Machine Learning
Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
Alexander Häußer
This paper investigates the performance of Echo State Networks (ESNs) for univariate
forecasting of monthly and quarterly time series from the M4
Forecasting Competition
dataset. We evaluate whether a simple first-order autoregressive ESN can serve as a competitive alternative to widely used
forecasting methods. The study uses a two-stage design: a Parameter
dataset is used to analyze ESN model configurations over leakage rate, spectral radius, reservoir size, and regularization selection, while a disjoint Forecast
dataset is reserved for out-of-sample benchmarking. Forecast accuracy is measured using mean absolute scaled error (MASE), symmetric mean absolute percentage error (sMAPE), and the overall weighted average (OWA). The ESN is compared with simple
benchmarks, statistical models including autoregressive integrated moving average (ARIMA), exponential smoothing state space (ETS), the Theta method, and TBATS, as well as multilayer perceptron (MLP), recurrent neural network (RNN), and hybrid exponential smoothing-RNN (ES-RNN)
benchmarks. The model-configuration analysis reveals frequency-specific patterns: monthly series tend to favor moderately persistent reservoirs, whereas quarterly series favor more contractive dynamics; across both frequencies, high leakage rates are generally preferred. In the final
benchmark, the ESN performs on par with ARIMA and TBATS under mean MASE for monthly data and achieves the second-lowest mean MASE for quarterly data. ES-RNN provides the best aggregate accuracy for both frequencies. Overall, the results indicate that a simple autoregressive ESN can provide competitive forecast accuracy on the considered filtered M4 subsets, particularly under MASE, while requiring low training and
forecasting time once the ESN configuration has been fixed.
Read the full abstract ▾
Machine Learning
The Role of Target Update Frequencies in Q-Learning
Simon Weissmann, Tilman Aach, Benedikt Wille et al. (+2 more)
The target network update frequency (TUF) is a central stabilization mechanism in (deep) Q-learning. However, their selection remains poorly understood and is often treated merely as another tunable hyperparameter rather than as a principled design decision. This work provides a theoretical analysis of target fixing in tabular Q-learning through the lens of approximate dynamic programming. We formulate periodic target updates as a nested optimization scheme in which each outer iteration applies an inexact Bellman optimality operator, approximated by a generic inner loop optimizer. Rigorous theory yields a finite-time convergence analysis for the asynchronous sampling setting, specializing to
stochastic gradient descent in the inner loop. Our results deliver an explicit characterization of the bias-variance trade-off induced by the target update period, showing how to optimally set this critical hyperparameter. We prove that constant target update schedules are suboptimal, incurring a logarithmic overhead in sample complexity that is entirely avoidable with adaptive schedules. Our analysis shows that the optimal target update frequency increases geometrically over the course of the learning process.
Read the full abstract ▾
All authors Simon Weissmann, Tilman Aach, Benedikt Wille, Sebastian Kassing, Leif Döring
Machine Learning
GeoIB: Geometry-Aware Information Bottleneck via Statistical-Manifold Compression
Weiqi Wang, Zhiyi Tian, Chenhan Zhang et al. (+1 more)
Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI)
estimators, rather than directly controlling the MI I(X;Z) itself. The looseness and
estimator-dependent bias can make IB "compression" only indirectly controlled and optimization fragile. We revisit the IB problem through the lens of information geometry and propose a
Geometric Information Bottleneck (GeoIB) that dispenses with mutual information (MI) estimation. We show that I(X;Z) and I(Z;Y) admit exact projection forms as minimal Kullback-Leibler (KL) distances from the joint distributions to their respective independence
manifolds. Guided by this view, GeoIB controls information compression with two complementary terms: (i) a distribution-level Fisher-Rao (FR) discrepancy, which matches KL to second order and is reparameterization-invariant; and (ii) a geometry-level Jacobian-Frobenius (JF) term that provides a local capacity-type upper bound on I(Z;X) by penalizing pullback volume expansion of the encoder. We further derive a natural-gradient optimizer consistent with the FR metric and prove that the standard additive natural-gradient step is first-order equivalent to the geodesic update. We conducted extensive experiments and observed that the GeoIB achieves a better trade-off between prediction accuracy and compression ratio in the information plane than the mainstream IB baselines on popular
datasets. GeoIB improves invariance and optimization stability by unifying distributional and
geometric regularization under a single bottleneck multiplier. The source code of GeoIB is released at "https://anonymous.4open.science/r/G-IB-0569".
Read the full abstract ▾
All authors Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Shui Yu
Machine Learning · Cross-listed from q-bio.QM
All-Atom GPCR-Ligand Dynamics Simulation via a Residual Latent Flow Mode
Jiying Zhang, Shuhao Zhang, Pierre Vandergheynst et al. (+1 more)
G-
protein-coupled receptors (GPCRs), which are targeted by over one-third of approved drugs, undergo intricate conformational transitions to transduce signals. While Molecular Dynamics (MD) is essential for elucidating this transduction process, particularly within ligand-bound complexes, conventional all-atom MD simulation is computationally prohibitive. In this paper, we introduce GPCRLMD, a deep generative framework for efficient all-atom GPCR-ligand simulation. GPCRLMD employs an Atom-Anchored Thermal Variational Autoencoder (AAT-VAE) to first map the complex into a regularized dimension-preserving latent space, maintaining
geometric topology via physics-informed constraints. Within this latent space, a Residual Latent Flow samples
evolution trajectories, which are subsequently decoded back to atomic coordinates. By capturing temporal dynamics via relative displacements anchored to the initial structure, this residual mechanism effectively decouples static
topology from dynamic fluctuations. Experimental results demonstrate that GPCRLMD achieves state-of-the-art performance in GPCR-ligand dynamics simulation, faithfully reproducing ensemble observables and critical ligand-receptor interactions.
Read the full abstract ▾
All authors Jiying Zhang, Shuhao Zhang, Pierre Vandergheynst, Patrick Barth
Machine Learning
NeuroPareto: Calibrated Acquisition for Costly Many-Goal Search in Vast Parameter Spaces
Rong Fu, Chunlei Meng, Haoyu Zhao et al. (+2 more)
The pursuit of optimal trade-offs in high-dimensional search spaces under stringent computational constraints poses a fundamental challenge for contemporary multi-objective optimization. We develop NeuroPareto, a cohesive architecture that integrates rank-centric filtering, uncertainty disentanglement, and history-conditioned acquisition strategies to navigate complex objective landscapes. A calibrated
Bayesian classifier estimates epistemic uncertainty across non-domination tiers, enabling rapid generation of high-quality candidates with minimal evaluation cost. Deep Gaussian Process surrogates further separate predictive uncertainty into reducible and irreducible components, providing refined predictive means and risk-aware signals for downstream selection. A lightweight acquisition network, trained online from historical hypervolume improvements, guides expensive evaluations toward regions balancing convergence and diversity. With hierarchical screening and amortized surrogate updates, the method maintains accuracy while keeping computational overhead low. Experiments on DTLZ and ZDT suites and a subsurface energy extraction task show that NeuroPareto consistently outperforms classifier-enhanced and surrogate-assisted baselines in Pareto proximity and hypervolume.
Read the full abstract ▾
All authors Rong Fu, Chunlei Meng, Haoyu Zhao, Kun Liu, Simon James Fong
Machine Learning · Cross-listed from stat.ML
Byzantine Machine Learning: MultiKrum and an optimal notion of robustness
Gilles Bareilles, Wassim Bouaziz, Julien Fageot et al. (+1 more)
Aggregation rules are the cornerstone of distributed (or
federated) learning in the presence of adversaries, under the so-called Byzantine threat model. They are also interesting mathematical objects from the point of view of robust mean estimation. The Krum aggregation rule has been extensively studied, and endowed with formal robustness and convergence guarantees. Yet, MultiKrum, a natural extension of Krum, is often preferred in practice for its superior empirical performance, even though no theoretical guarantees were available until now. In this work, we provide the first proof that MultiKrum is a robust aggregation rule, and bound its robustness coefficient. To do so, we introduce $\kappa^\star$, the optimal *robustness coefficient* of an aggregation rule, which quantifies the accuracy of mean estimation in the presence of adversaries in a tighter manner compared with previously adopted notions of robustness. We then construct an upper and a lower bound on MultiKrum's robustness coefficient. As a by-product, we also improve on the best-known bounds on Krum's robustness coefficient. We show that MultiKrum's bounds are never worse than Krum's, and better in realistic regimes. We illustrate this analysis by an experimental investigation on the quality of the lower bound.
Read the full abstract ▾
All authors Gilles Bareilles, Wassim Bouaziz, Julien Fageot, El-Mahdi El-Mhamdi
Machine Learning · Cross-listed from stat.ML
A hitchhiker's guide to Poisson gradient estimation
Michael Ibrahim, Hanqi Zhao, Eli Sennesh et al. (+5 more)
Poisson-distributed latent variable models are widely used in computational neuroscience, but differentiating through discrete
stochastic samples remains challenging. Two approaches address this: *Exponential Arrival Time* (EAT) simulation and *Gumbel-SoftMax* (GSM) relaxation. We provide the first systematic comparison of these methods, along with practical guidance for practitioners. Our main technical contribution is a modification to the EAT method that theoretically guarantees an unbiased first moment (exactly matching the firing rate), and reduces second-moment bias. We evaluate these methods on their distributional fidelity, gradient quality, and performance on two tasks: (1) variational autoencoders with Poisson latents, and (2) partially observable generalized linear models, where latent neural connectivity must be inferred from observed spike trains. Across all metrics, our modified EAT method exhibits better overall performance (often comparable to exact gradients), and substantially higher robustness to hyperparameter choices. These results extend to over-dispersed Negative Binomial latents, where modified EAT again performs best. However, only GSM generalizes to arbitrary non-Poisson distributions, including the under-dispersed regime. Together, our results clarify the trade-offs between these methods and offer concrete recommendations for practitioners working with Poisson latent variable models.
Read the full abstract ▾
All authors Michael Ibrahim, Hanqi Zhao, Eli Sennesh, Zhi Li, Anqi Wu, Jacob L. Yates, Chengrui Li, Hadi Vafaii
Machine Learning · Cross-listed from cs.CV
Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMs
Xuwei Tan, Ziyu Hu and Xueru Zhang
Machine learning models trained on real-world data often inherit and amplify biases against certain social groups, raising urgent concerns about their deployment at scale. While numerous bias mitigation methods have been proposed, comparing the effectiveness of bias mitigation methods remains difficult due to heterogeneous
datasets, inconsistent
fairness metrics, isolated evaluation of
vision versus multi-modal models, and insufficient hyperparameter tuning that undermines fair comparisons. We introduce NH-Fair, a unified
benchmark for
fairness without harm that spans both
vision models and large
vision-
language models (LVLMs) under standardized data, metrics, and training protocols, covering supervised and zero-shot regimes. Our key contributions are: (1) a systematic ERM tuning study that identifies training choices with large influence on both utility and disparities, yielding empirically grounded guidelines to help practitioners reduce expensive hyperparameter tuning space in achieving strong
fairness and accuracy; (2) evidence that many debiasing methods do not reliably outperform a well-tuned ERM baseline, whereas a composite data-augmentation method consistently delivers parity gains without sacrificing utility, emerging as a promising practical strategy. (3) an analysis showing that while LVLMs achieve higher average accuracy, they still exhibit subgroup disparities, and gains from scaling are typically smaller than those from architectural or training-protocol choices. NH-Fair provides a reproducible, tuning-aware pipeline for rigorous, harm-aware
fairness evaluation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation
Jinxing Zhou, Yanghao Zhou, Yaoting Wang et al. (+5 more)
Language-referred audio-visual
segmentation (Ref-AVS) aims to segment target objects described by natural
language by jointly
reasoning over
video, audio, and text. Beyond generating
segmentation masks, providing rich and interpretable diagnoses of mask quality remains largely underexplored. In this work, we introduce Mask Quality Assessment in the Ref-AVS context (MQA-RefAVS), a new task that evaluates the quality of candidate
segmentation masks without relying on ground-truth annotations as references at inference time. Given audio-visual-
language inputs and each provided
segmentation mask, the task requires estimating its IoU with the unobserved ground truth, identifying the corresponding error type, and recommending an actionable quality-control decision. To support this task, we construct MQ-RAVSBench, a
benchmark featuring diverse and representative mask error modes that span both
geometric and semantic issues. We further propose MQ-Auditor, a
multimodal large
language model (MLLM)-based auditor that explicitly reasons over
multimodal cues and mask information to produce quantitative and qualitative mask quality assessments. Extensive experiments demonstrate that MQ-Auditor outperforms strong open-source and commercial MLLMs and can be integrated with existing Ref-AVS systems to detect
segmentation failures and support downstream
segmentation improvement. Data and codes will be released at https://github.com/jasongief/MQA-RefAVS.
Read the full abstract ▾
All authors Jinxing Zhou, Yanghao Zhou, Yaoting Wang, Zongyan Han, Jiaqi Ma, Henghui Ding, Rao Muhammad Anwer, Hisham Cholakkal
Machine Learning · Cross-listed from stat.ML
Transcendental Regularization of Finite Mixtures:Theoretical Guarantees and Practical Limitations
Ernest Fokoué
Finite mixture models are widely used for unsupervised learning, but maximum likelihood estimation via EM suffers from degeneracy as components collapse. We introduce transcendental regularization, a penalized likelihood framework with analytic barrier functions that prevent degeneracy while maintaining asymptotic efficiency. The resulting Transcendental
Algorithm for Mixtures of Distributions (TAMD) offers strong theoretical guarantees: identifiability, consistency, and robustness. Empirically, TAMD successfully stabilizes estimation and prevents collapse, yet achieves only modest improvements in classification accuracy-highlighting fundamental limits of mixture models for unsupervised learning in high dimensions. Our work provides both a novel theoretical framework and an honest assessment of practical limitations, implemented in an open-source R package.
Read the full abstract ▾
Machine Learning · Cross-listed from q-bio.QM
Prenatal Stress Detection from Electrocardiography Using Self-Supervised Deep Learning: Development and External Validation
Martin G. Frasch, Marlene J.E. Mayer, Clara Becker et al. (+4 more)
Prenatal psychological stress affects 15-25% of pregnancies and increases risks of preterm birth, low birth weight, and adverse neurodevelopmental outcomes. Current screening relies on subjective questionnaires (PSS-10), limiting continuous monitoring. We developed deep learning models for stress detection from electrocardiography (ECG) using the FELICITy 1 cohort (151 pregnant women, 32-38 weeks gestation). A ResNet-34 encoder was pretrained via SimCLR contrastive learning on 40,692 ECG segments per subject. Multi-layer feature extraction enabled binary classification and continuous PSS prediction across maternal (mECG), fetal (fECG), and abdominal ECG (aECG). External validation used the FELICITy 2 RCT (28 subjects, different ECG device, yoga intervention vs. control). On FELICITy 1 (5-fold CV): mECG 98.6% accuracy (R2=0.88, MAE=1.90), fECG 99.8% (R2=0.95, MAE=1.19), aECG 95.5% (R2=0.75, MAE=2.80). External validation on FELICITy 2: mECG 77.3% accuracy (R2=0.62, MAE=3.54, AUC=0.826), aECG 63.6% (R2=0.29, AUC=0.705). Signal quality-based channel selection outperformed all-channel averaging (+12% R2 improvement). Mixed-effects models detected a significant intervention response (p=0.041). Self-supervised deep learning on pregnancy ECG enables accurate, objective stress assessment, with multi-layer feature extraction substantially outperforming single
embedding approaches.
Read the full abstract ▾
All authors Martin G. Frasch, Marlene J.E. Mayer, Clara Becker, Peter Zimmermann, Camilla Zelgert, Marta C. Antonelli, Silvia M. Lobmaier
Machine Learning · Cross-listed from cs.CV
Explainable Computer Vision Framework for Automated Pore Detection and Criticality Assessment in Additive Manufacturing
Akshansh Mishra and Rakesh Morisetty
Internal porosity remains a critical defect mode in additively manufactured components, compromising structural performance and limiting industrial adoption. Automated defect detection methods exist but lack interpretability, preventing engineers from understanding the physical basis of criticality predictions. This study presents an explainable computer
vision framework for pore detection and criticality assessment in three-dimensional tomographic volumes. Sequential grayscale slices were reconstructed into volumetric
datasets, and intensity-based thresholding with connected component analysis identified 500 individual pores. Each pore was characterized using
geometric descriptors including size, aspect ratio, extent, and spatial position relative to the specimen boundary. A pore interaction network was constructed using percentile-based Euclidean distance criteria, yielding 24,950 inter-pore connections. Machine learning models predicted pore criticality scores from extracted features, and SHAP analysis quantified individual feature contributions. Results demonstrate that normalized surface distance dominates model predictions, contributing more than an order of magnitude greater importance than all other descriptors. Pore size provides minimal influence, while
geometric parameters show negligible impact. The strong inverse relationship between surface proximity and criticality reveals boundary-driven failure mechanisms. This interpretable framework enables transparent defect assessment and provides actionable insights for process optimization and quality control in additive manufacturing.
Read the full abstract ▾
Machine Learning
PLATE: Plasticity-Tunable Efficient Adapters for Geometry-Aware Continual Learning
Romain Cosentino
We develop a continual learning method for pretrained models that requires no access to old-task data, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key observation is that pretrained networks exhibit substantial
geometric redundancy, and that this redundancy can be exploited in two complementary ways. First, redundant
neurons provide a proxy for dominant pretraining-era feature directions, enabling the construction of approximately protected update subspaces directly from pretrained weights. Second, redundancy offers a natural bias for where to place plasticity: by restricting updates to a subset of redundant
neurons and constraining the remaining degrees of freedom, we obtain update families with reduced functional drift on the old-data distribution and improved worst-case retention guarantees. These insights lead to PLATE (Plasticity-Tunable Efficient Adapters), a continual learning method requiring no past-task data that provides explicit control over the plasticity-retention trade-off. PLATE parameterizes each layer with a structured low-rank update $\Delta W = B A Q^\top$, where $B$ and $Q$ are computed once from pretrained weights and kept frozen, and only $A$ is trained on the new task. The code is available at https://github.com/SalesforceAIResearch/PLATE.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.NE
Devroop Kar, Daniel Krutz and Travis Desell
Designing effective
quantum circuits remains a central challenge in
quantum computing, as
circuit structure strongly influences expressivity, trainability, and hardware feasibility. Current approaches, whether using manually designed
circuit templates, fixed heuristics, or automated rules, face limitations in scalability, flexibility, and adaptability, often producing
circuits that are poorly matched to the specific problem or
quantum hardware. In this work, we propose the Evolutionary eXploration of Augmenting
Quantum Circuits (EXAQC), an evolutionary approach to the automated design and training of parameterized
quantum circuits (PQCs) which leverages and extends on strategies from neuroevolution and genetic programming. The proposed method jointly searches over gate types,
qubit connectivity, parameterization, and
circuit depth while respecting hardware and noise constraints. The method supports both Qiskit and Pennylane libraries, allowing the user to configure every aspect. This work highlights evolutionary search as a critical tool for advancing
quantum machine learning and variational
quantum algorithms, providing a principled pathway toward scalable, problem-aware, and hardware-efficient
quantum circuit design. Preliminary results demonstrate that
circuits evolved on classification tasks are able to achieve over 90% accuracy on most of the
benchmark datasets with a limited computational budget, and are able to emulate target
circuit quantum states with high fidelity scores.
Read the full abstract ▾
Machine Learning
Understanding and Exploiting Weight Update Sparsity for Communication-Efficient Distributed RL
Erfan Miahi and Eugene Belilovsky
Bandwidth-constrained distributed reinforcement learning (RL) post-training of large
language models is bottlenecked by two channels: weight synchronization from trainers to inference workers, and gradient or pseudo-gradient synchronization across trainers. We find that approximately 99% of per-step weight updates are invisible after the BF16 cast used by standard training and inference forward passes. We explain this sparsity by showing that, at typical RL post-training learning rates, Adam updates often fall below the local BF16 rounding threshold. We turn this observation into an algorithmic principle called compute-visible sparsification: transmit only updates that would change the next forward pass. PULSE (Precision-gated Updates for Low-precision Sparse Exchange) turns this principle into two communication
algorithms: PULSESync sends lossless sparse BF16 weight patches from trainers to inference workers, and PULSELoCo sparsifies DiLoCo-style FP32 pseudo-gradient synchronization with error feedback. Over bandwidth-constrained commodity networks, PULSESync cuts weight-synchronization communication by over 100x while reconstructing trainer weights bit-identically. PULSELoCo matches DiLoCo across four models while reducing trainer-to-trainer communication by over 17x versus DiLoCo and over 100x versus DDP in the largest evaluated setting.
Read the full abstract ▾
Machine Learning
The Geometry of Learning to Avoid Interventions
Ethan Pronovost, Khimya Khetarpal and Siddhartha Srinivasa
Human interventions are a common source of supervision in autonomous systems during deployment. Many existing approaches are based on avoiding interventions, yet the consequences of this objective are not well understood. We develop a
geometric perspective on intervention learning that characterizes intervention avoidance as constraining policies to a face of the occupancy measure polytope. This view reveals that the effectiveness of intervention learning depends on the informativeness of the intervention strategy: highly informative interventions uniquely determine the solution, while weak interventions leave a large set of feasible policies, many of which are suboptimal. Motivated by this under-specification, we define Robust Intervention Learning (RIL) as the problem of learning policies that perform well under varying levels of intervention informativeness. From the
geometric formulation, we derive Residual Intervention Fine-Tuning (RIFT), which combines interventions with a prior policy to select among feasible solutions. We show that RIFT provides provable improvement over the prior and corresponds to solving a constrained reinforcement learning problem with an induced reward. Empirically, RIFT yields consistent policy improvement across a range of intervention settings, particularly when interventions are sparse or weakly informative. These results highlight the importance of accounting for intervention informativeness and suggest a principled path toward robust learning from human feedback.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Preference-based Conditional Treatment Effects and Policy Learning
Dovid Parnas, Mathieu Even, Julie Josse et al. (+1 more)
We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment Effect (CPTE). CPTE requires only that outcomes be ranked under a preference rule, unlocking flexible modeling of heterogeneous effects with multivariate, ordinal, or preference-driven outcomes. This unifies applications such as conditional probability of necessity and sufficiency, conditional Win Ratio, and Generalized Pairwise Comparisons. Despite the intrinsic non-identifiability of comparison-based estimands, CPTE provides interpretable targets and delivers new identifiability conditions for previous unidentifiable estimands. We present estimation strategies via matching,
quantile, and distributional regression, and further design efficient influence-function
estimators to correct plug-in bias and maximize policy value. Synthetic and semi-synthetic experiments demonstrate clear performance gains and practical impact.
Read the full abstract ▾
All authors Dovid Parnas, Mathieu Even, Julie Josse, Uri Shalit
Machine Learning
SymPlex: A Structure-Aware Transformer for Symbolic PDE Solving
Yesom Park, Annie C. Lu, Shao-Ching Huang et al. (+3 more)
We propose SymPlex, a reinforcement learning framework for discovering analytical symbolic solutions to partial differential equations (PDEs) without access to ground-truth expressions. SymPlex formulates symbolic PDE solving as tree-structured decision-making and optimizes candidate solutions using only the PDE and its boundary conditions. At its core is SymFormer, a structure-aware
Transformer that models hierarchical symbolic dependencies via tree-relative self-
attention and enforces syntactic validity through grammar-constrained autoregressive decoding, overcoming the limited expressivity of sequence-based generators. Unlike numerical and neural approaches that approximate solutions in discretized or implicit function spaces, SymPlex operates directly in symbolic expression space, enabling interpretable and human-readable solutions that naturally represent non-smooth behavior and explicit parametric dependence. Empirical results demonstrate exact recovery of non-smooth and parametric PDE solutions using deep learning-based symbolic methods.
Read the full abstract ▾
All authors Yesom Park, Annie C. Lu, Shao-Ching Huang, Qiyang Hu, Y. Sungtaek Ju, Stanley Osher
Machine Learning · Cross-listed from cs.CV
Dingkun Zhang, Shuhan Qi, Yulin Wu et al. (+3 more)
Multimodal Large
Language Models (MLLMs) suffer from severe training inefficiency issue, which is associated with their massive model sizes and visual
token numbers. Existing efforts in efficient training focus on reducing model sizes or trainable parameters. Inspired by the success of Visual
Token Pruning (VTP) in improving inference efficiency, we are exploring another substantial research direction for efficient training by reducing visual
tokens. However, applying VTP at the training stage results in a training-inference mismatch:
pruning-trained models perform poorly when inferring on non-pruned full visual
token sequences. To close this gap, we propose DualSpeed, a fast-slow framework for efficient training of MLLMs. The fast-mode is the primary mode, which incorporates existing VTP methods as plugins to reduce visual
tokens, along with a mode isolator to isolate the model's behaviors. The slow-mode is the auxiliary mode, where the model is trained on full visual sequences to retain training-inference consistency. To boost its training, it further leverages self-
distillation to learn from the sufficiently trained fast-mode. Together, DualSpeed can achieve both training efficiency and non-degraded performance. Experiments show DualSpeed accelerates the training of LLaVA-1.5 by 2.1$\times$ and LLaVA-NeXT by 4.0$\times$, retaining over 99% performance. Code: https://github.com/dingkun-zhang/DualSpeed
Read the full abstract ▾
All authors Dingkun Zhang, Shuhan Qi, Yulin Wu, Xinyu Xiao, Xuan Wang, Long Chen
Machine Learning · Cross-listed from cs.AI
Conformal Thinking: Risk Control for Reasoning on a Compute Budget
Xi Wang, Anushri Suresh, Alvin Zhang et al. (+6 more)
Reasoning Large
Language Models (LLMs) enable test-time scaling, with
dataset-level accuracy improving as the
token budget increases, motivating adaptive
reasoning – spending
tokens when they improve reliability and stopping early when additional computation is unlikely to help. However, setting the
token budget, as well as the threshold for adaptive
reasoning, is a practical challenge that entails a fundamental risk-accuracy trade-off. We re-frame the budget setting problem as risk control, limiting the error rate while minimizing compute. Our framework introduces an upper threshold that stops
reasoning when the model is confident (risking incorrect output) and a novel parametric lower threshold that preemptively stops unsolvable instances (risking premature stoppage). Given a target risk and a validation set, we use distribution-free risk control to optimally specify these stopping mechanisms. For scenarios with multiple budget controlling criteria, we incorporate an efficiency loss to select the most computationally efficient exiting mechanism. Empirical results across diverse
reasoning tasks and models demonstrate the effectiveness of our risk control approach, demonstrating computational efficiency gains from the lower threshold and ensemble stopping mechanisms while adhering to the user-specified risk target.
Read the full abstract ▾
All authors Xi Wang, Anushri Suresh, Alvin Zhang, Rishi More, William Jurayj, Benjamin Van Durme, Mehrdad Farajtabar, Daniel Khashabi, Eric Nalisnick
Machine Learning
Antidistillation Fingerprinting
Yixuan Even Xu, John Kirchenbauer, Yash Savani et al. (+5 more)
Model
distillation enables efficient emulation of frontier large
language models (LLMs), creating a need for robust mechanisms to detect when a third-party student model has trained on a teacher model's outputs. However, existing fingerprinting techniques that could be used to detect such
distillation rely on heuristic perturbations that impose a steep trade-off between generation quality and fingerprinting strength, often requiring significant degradation of utility to ensure the fingerprint is effectively internalized by the student. We introduce antidistillation fingerprinting (ADFP), a principled approach that aligns the fingerprinting objective with the student's learning dynamics. Building upon the gradient-based framework of antidistillation sampling, ADFP utilizes a proxy model to identify and sample
tokens that directly maximize the expected detectability of the fingerprint in the student after fine-tuning, rather than relying on the incidental absorption of the un-targeted biases of a more naive watermark. Experiments on GSM8K, OASST1, and MBPP demonstrate that ADFP achieves a significant Pareto improvement over state-of-the-art baselines, yielding stronger detection confidence with minimal impact on utility across mathematical
reasoning, dialogue, and code generation, even when the student model's architecture is unknown.
Read the full abstract ▾
All authors Yixuan Even Xu, John Kirchenbauer, Yash Savani, Asher Trockman, Alexander Robey, Tom Goldstein, Fei Fang, J. Zico Kolter
Machine Learning
Enhancing Imbalanced Node Classification via Curriculum-Guided Feature Learning and Three-Stage Attention Network
Abdul Joseph Fofanah, Lian Wen, David Chen et al. (+1 more)
Imbalanced node classification in graph neural networks (GNNs) happens when some labels are much more common than others, which causes the model to learn unfairly and perform badly on the less common classes. To solve this problem, we propose a Curriculum-Guided Feature Learning and Three-Stage
Attention Network (CL3AN-GNN), a learning network that uses a three-step
attention system (Engage, Enact, Embed) similar to how humans learn. The model begins by engaging with structurally simpler features, defined as (1) local neighbourhood patterns (1-hop), (2) low-degree node attributes, and (3) class-separable node pairs identified via initial graph convolutional networks and graph
attention networks (GCN and GAT)
embeddings. This foundation enables stable early learning despite label skew. The Enact stage then addresses complicated aspects: (1) connections that require multiple steps, (2) edges that connect different types of nodes, and (3) nodes at the edges of minority classes by using adjustable
attention weights. Finally, Embed consolidates these features via iterative message passing and curriculum-aligned loss weighting. We evaluate CL3AN-GNN on eight Open Graph
Benchmark datasets spanning social, biological, and citation networks. Experiments show consistent improvements across all
datasets in accuracy, F1-score, and AUC over recent state-of-the-art methods. The model's step-by-step method works well with different types of graph
datasets, showing quicker results than training everything at once, better performance on new, imbalanced graphs, and clear explanations of each step using gradient stability and
attention correlation learning curves. This work provides both a theoretically grounded framework for curriculum learning in GNNs and practical evidence of its effectiveness against imbalances, validated through metrics, convergence speeds, and generalisation tests.
Read the full abstract ▾
All authors Abdul Joseph Fofanah, Lian Wen, David Chen, Shaoyang Zhang
Machine Learning
COBALT: Contextual Bandit Learning with Offline Trajectories for Multi-Turn Code Generation
Ziru Chen, Dongdong Chen, Ruinan Jin et al. (+3 more)
Training large
language models (LLMs) for multi-turn code generation typically relies on online reinforcement learning (RL), in which models learn from repeatedly generated online rollouts. Although effective, online RL can be costly and unstable. In this paper, we present contextual bandit learning with offline trajectories (COBALT), a simple method that reuses offline multi-turn trajectories to efficiently train LLMs for multi-turn code generation. Building on the observation that multi-turn code generation is a one-step recoverable Markov decision process, COBALT first collects code generation trajectories using a reference LLM and divides them into partial trajectories. Then, during online bandit learning, the LLM is trained to complete each partial trajectory through single-step code generation. On LiveCodeBench, COBALT substantially improves R1-Distill 8B and Qwen3 8B by up to 9.0 and 6.2 absolute Pass@1 points and matches the performance of two multi-turn online RL baselines using GRPO and VeRPO. We also perform a perturbation-based analysis of in-context reward hacking and show that Cobalt can improve robustness to misleading execution feedback. Overall, our results demonstrate that Cobalt is a promising solution for multi-turn code generation. Our code and data are available at https://github.com/OSU-NLP-Group/cobalt.
Read the full abstract ▾
All authors Ziru Chen, Dongdong Chen, Ruinan Jin, Yingbin Liang, Yujia Xie, Huan Sun
Machine Learning
Prediction of Critical Heat Flux in Rod Bundles Using Tube-Based Hybrid Machine Learning Models in CTF
Aidan Furlong, Robert Salko, Xingang Zhao et al. (+1 more)
The prediction of critical heat flux (CHF) using machine learning (ML) approaches has become a highly active research activity in recent years, the goal of which is to build models more accurate than current conventional approaches such as empirical correlations or lookup tables (LUTs). Previous work developed and deployed tube-based pure and hybrid ML models in the CTF subchannel code, however, full-scale reactor core simulations require the use of rod bundle geometries. Unlike isolated subchannels, rod bundles experience complex thermal hydraulic phenomena such as channel crossflow, spacer grid losses, and effects from unheated conductors. This study investigates the generalization of ML-based CHF prediction models in rod bundles after being trained on tube-based CHF data. A purely data-driven DNN and two hybrid bias-correction models were implemented in the CTF subchannel code and used to predict CHF location and magnitude in the Combustion Engineering 5-by-5 bundle CHF test series. The W-3 correlation, Bowring correlation, and Groeneveld LUT were used as baseline comparators. On average, all three ML-based approaches produced magnitude and location predictions more accurate than the baseline models, with the hybrid LUT model exhibiting the most favorable performance metrics.
Read the full abstract ▾
All authors Aidan Furlong, Robert Salko, Xingang Zhao, Xu Wu
Machine Learning
Ananya Parashar, Derek Long, Dwaipayan Saha et al. (+1 more)
We present a new paradigm for creating random features to approximate bi-variate functions (in particular, kernels) defined on general
manifolds. This new mechanism of
Manifold Random Features (MRFs) leverages discretization of the
manifold and the recently introduced technique of Graph Random Features (GRFs) to learn continuous fields on
manifolds. Those fields are used to find continuous approximation mechanisms that otherwise, in general scenarios, cannot be derived analytically. MRFs provide positive and bounded features, a key property for accurate, low-variance approximation. We show deep asymptotic connection between GRFs, defined on discrete graph objects, and continuous random features used for regular kernels. As a by-product of our method, we re-discover recently introduced mechanism of Gaussian kernel approximation applied in particular to improve linear-
attention Transformers, considering simple random walks on graphs and by-passing original complex mathematical computations. We complement our
algorithm with a rigorous theoretical analysis and verify in thorough experimental studies.
Read the full abstract ▾
All authors Ananya Parashar, Derek Long, Dwaipayan Saha, Krzysztof Choromanski
Machine Learning · Cross-listed from cs.AI
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Yingxuan Yang, Chengrui Qu, Muning Wen et al. (+5 more)
LLM-based multi-
agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance by increasing the number of
agents; however, we find that such scaling exhibits strong diminishing returns in homogeneous settings, while introducing heterogeneity (e.g., different models,
prompts, or tools) continues to yield substantial gains. This raises a fundamental question: what limits scaling, and why does diversity help? We present an information-theoretic framework showing that MAS performance is bounded by the intrinsic task uncertainty, not by
agent count. We derive architecture-agnostic bounds demonstrating that improvements depend on how many effective channels the system accesses. Homogeneous
agents saturate early because their outputs are strongly correlated, whereas heterogeneous
agents contribute complementary evidence. We further introduce $K^*$, an effective channel count that quantifies the number of effective channels without ground-truth labels. Empirically, we show that heterogeneous configurations consistently outperform homogeneous scaling: 2 diverse
agents can match or exceed the performance of 16 homogeneous
agents. Our results provide principled guidelines for building efficient and robust MAS through diversity-aware design. Code and
Dataset are available at the link: https://github.com/SafeRL-Lab/
Agent-Scaling.
Read the full abstract ▾
All authors Yingxuan Yang, Chengrui Qu, Muning Wen, Laixi Shi, Ying Wen, Weinan Zhang, Adam Wierman, Shangding Gu
Machine Learning
Should I use Synthetic Data for That? An Analysis of the Suitability of Synthetic Data for Data Sharing and Augmentation
Bogdan Kulynych, Theresa Stadler, Jean Louis Raisaro et al. (+1 more)
Recent advances in generative modelling have led many to see synthetic data as the go-to solution for a range of problems around data access, scarcity, and under-representation. In this paper, we study three prominent use cases: (1) Sharing synthetic data as a proxy for proprietary
datasets to enable statistical analyses while protecting
privacy, (2) Augmenting machine learning training sets with synthetic data to improve model performance, and (3) Augmenting
datasets with synthetic data to reduce variance in statistical estimation. For each use case, we formalise the problem setting and study, through formal analysis and case studies, under which conditions synthetic data can achieve its intended objectives. We identify fundamental and practical limits that constrain when synthetic data can serve as an effective solution for a particular problem. Our analysis reveals that due to these limits many existing or envisioned use cases of synthetic data are a poor problem fit. Our formalisations and classification of synthetic data use cases enable decision makers to assess whether synthetic data is a suitable approach for their specific data availability problem.
Read the full abstract ▾
All authors Bogdan Kulynych, Theresa Stadler, Jean Louis Raisaro, Carmela Troncoso
Machine Learning · Cross-listed from stat.ML
Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants
Gabriel Damsholt, Jes Frellsen and Susanne Ditlevsen
Stochastic interpolants unify flows and
diffusions, popular generative modeling frameworks. A primary hyperparameter in these methods is the interpolation schedule that determines how to bridge a standard Gaussian base measure to an arbitrary target measure. We prove how to convert a sample path of a
stochastic differential equation (SDE) with arbitrary
diffusion coefficient under any schedule into the unique sample path under another arbitrary schedule and
diffusion coefficient. We then extend the
stochastic interpolant framework to admit a larger class of point mass schedules in which the Gaussian base measure collapses to a point mass measure. Under the assumption of Gaussian data, we identify lazy schedule families that make the drift identically zero and show that with deterministic sampling one gets a variance-preserving schedule commonly used in
diffusion models, whereas with statistically optimal SDE sampling one gets our point mass schedule. Finally, to demonstrate the usefulness of our theoretical results on realistic highly non-Gaussian data, we apply our lazy schedule conversion to a state-of-the-art pretrained flow model and show that this allows for generating images in fewer steps without retraining the model.
Read the full abstract ▾
Machine Learning
Inference-time Unlearning Using Conformal Prediction
Somnath Basu Roy Chowdhury, Rahul Kidambi, Avinava Dubey et al. (+4 more)
Machine unlearning is the process of efficiently removing specific information from a trained machine learning model without retraining from scratch. Existing unlearning methods, which often provide provable guarantees, typically involve retraining a subset of model parameters based on a forget set. While these approaches show promise in certain scenarios, their underlying assumptions are often challenged in real-world applications – particularly when applied to generative models. Furthermore, updating parameters using these unlearning procedures often degrades the general-purpose capabilities the model acquired during pre-training. Motivated by these shortcomings, this paper considers the paradigm of inference time unlearning – wherein, the generative model is equipped with an (approximately correct) verifier that judges whether the model's response satisfies appropriate unlearning guarantees. This paper introduces a framework that iteratively refines the quality of the generated responses using feedback from the verifier without updating the model parameters. The proposed framework leverages conformal prediction to reduce computational overhead and provide distribution-free unlearning guarantees. This paper's approach significantly outperforms existing state-of-the-art methods, reducing unlearning error by up to 93% across challenging unlearning
benchmarks.
Read the full abstract ▾
All authors Somnath Basu Roy Chowdhury, Rahul Kidambi, Avinava Dubey, David Wang, Gokhan Mergen, Amr Ahmed, Aranyak Mehta
Machine Learning
Efficient Estimation of Kernel Surrogate Models for Task Attribution
Zhenshuo Zhang, Minxuan Duan and Hongyang R. Zhang
Modern AI
agents such as large
language models are trained on diverse tasks – translation, code generation, mathematical
reasoning, and text prediction – simultaneously. A key question is how to quantify the influence of each individual training task on performance on a target task, a problem we refer to as task attribution. The direct approach, leave-one-out retraining, measures the effect of removing each task, but is computationally infeasible at scale. An alternative approach that builds surrogate models to predict the performance on a target task for any subset of training tasks has emerged in the recent literature. Prior work focuses on linear surrogate models, which capture first-order relationships but miss nonlinear interactions such as XOR-type effects. In this paper, we first consider a unified task-weighting framework for analyzing task-attribution methods and establish a new connection between linear surrogate models and influence functions via a second-order analysis. Then, we introduce kernel surrogate models, which more effectively represent second-order task interactions. To efficiently learn the kernel surrogate, we develop a gradient-based estimation procedure that leverages a first-order approximation of pretrained models; empirically, this yields accurate surrogate estimates with less than $2\%$ relative error without repeated retraining. Experiments across multiple settings – including mathematical
reasoning in
transformers, in-context learning, and multi-objective reinforcement learning – demonstrate the effectiveness of kernel surrogate models. They achieve a $25\%$ higher correlation with the leave-one-out ground truth than linear surrogates and influence-function baselines, enabling more accurate and scalable task attribution. When used for downstream data selection, kernel surrogate models further yield a $40\%$ improvement in the aforementioned settings.
Read the full abstract ▾