Machine Learning · Cross-listed from stat.ML
Reliable Real-Time Value at Risk Estimation via Quantile Regression Forest with Conformal Calibration
Du-Yi Wang, Guo Liang, Kun Zhang et al. (+1 more)
Rapidly evolving
market conditions call for real-time risk monitoring, but its online estimation remains challenging. In this paper, we study the online estimation of one of the most widely used risk measures, Value at Risk (VaR). Its accurate and reliable estimation is essential for timely risk control and informed decision-making. We propose to use the
quantile regression forest in the offline-simulation-online-estimation (OSOA) framework. Specifically, the
quantile regression forest is trained offline to learn the relationship between the online VaR and risk factors, and real-time VaR estimates are then produced online by incorporating observed risk factors. To further ensure reliability, we develop a conformalized
estimator that calibrates the online VaR estimates. To the best of our knowledge, we are the first to leverage conformal calibration to estimate real-time VaR reliably based on the OSOA formulation. Theoretical analysis establishes the consistency and coverage validity of the proposed
estimators. Numerical experiments confirm the proposed method and demonstrate its effectiveness in practice.
Read the full abstract ▾
All authors Du-Yi Wang, Guo Liang, Kun Zhang, Qianwen Zhu
Machine Learning · Cross-listed from physics.geo-ph
Propagating the prior from far to near offset: A self-supervised diffusion framework for progressively recovering near-offsets of towed-streamer data
Shijun Cheng and Tariq Alkhalifah
In marine towed-streamer seismic acquisition, the nearest hydrophone is often two hundred meter away from the source resulting in missing near-offset traces, which degrades critical processing workflows such as surface-related multiple elimination, velocity analysis, and full-waveform inversion. Existing reconstruction methods, like transform-domain interpolation, often produce kinematic inconsistencies and amplitude distortions, while supervised deep learning approaches require complete ground-truth near-offset data that are unavailable in realistic acquisition scenarios. To address these limitations, we propose a self-supervised
diffusion-based framework that reconstructs missing near-offset traces without requiring near-offset reference data. Our method leverages overlapping patch extraction with single-trace shifts from the available far-offset section to train a conditional
diffusion model, which learns offset-dependent statistical patterns governing event
curvature, amplitude variation, and wavelet characteristics. At inference, we perform trace-by-trace recursive extrapolation from the nearest recorded offset toward zero offset, progressively propagating learned prior information from far to near offsets. The generative formulation further provides uncertainty estimates via ensemble sampling, quantifying prediction confidence where validation data are absent. Controlled validation experiments on synthetic and field
datasets show substantial performance gains over conventional
parabolic Radon transform baselines. Operational deployment on actual near-offset gaps demonstrates practical viability where ground-truth validation is impossible. Notably, the reconstructed waveforms preserve realistic amplitude-versus-offset trends despite training exclusively on far-offset observations, and uncertainty maps accurately identify challenging extrapolation regions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Learning Sparse Visual Representations via Spatial-Semantic Factorization
Theodore Zhengde Zhao, Sid Kiblawi, Jianwei Yang et al. (+6 more)
Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global
tokens that are forced to be location-invariant for augmentation
alignment, a process that inherently discards the spatial coordinates required for reconstruction. Conversely, generative SSL (e.g., MAE) preserves dense feature grids for reconstruction but fails to produce high-level abstractions. We introduce
STELLAR, a framework that resolves this tension by factorizing visual features into a low-rank product of semantic concepts and their spatial distributions. This disentanglement allows us to perform DINO-style augmentation
alignment on the semantic
tokens while maintaining the precise spatial mapping in the localization
matrix necessary for pixel-level reconstruction. We demonstrate that as few as 16 sparse
tokens under this factorized form are sufficient to simultaneously support high-quality reconstruction (2.60 FID) and match the semantic performance of dense backbones (79.10% ImageNet accuracy). Our results highlight
STELLAR as a versatile sparse representation that bridges the gap between discriminative and generative
vision by strategically separating semantic identity from spatial geometry. Code available at https://aka.ms/
stellar.
Read the full abstract ▾
All authors Theodore Zhengde Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel C Codella, Tristan Naumann, Hoifung Poon, Mu Wei
Machine Learning
Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
Mingyi Li, Taira Tsuchiya and Kenji Yamanishi
This work studies online episodic tabular Markov decision processes (MDPs) with known transitions and develops best-of-both-worlds
algorithms that achieve refined data-dependent regret bounds in the
adversarial regime and variance-dependent regret bounds in the
stochastic regime. We quantify MDP complexity using a first-order quantity and several new data-dependent measures for the
adversarial regime, including a second-order quantity and a path-length measure, as well as variance-based measures for the
stochastic regime. To adapt to these measures, we develop
algorithms based on global optimization and policy optimization, both built on optimistic follow-the-regularized-leader with log-barrier regularization. For global optimization, our
algorithms achieve first-order, second-order, and path-length regret bounds in the
adversarial regime, and in the
stochastic regime, they achieve a variance-aware gap-independent bound and a variance-aware gap-dependent bound that is polylogarithmic in the number of episodes. For policy optimization, our
algorithms achieve the same data- and variance-dependent adaptivity, up to a factor of the episode horizon, by exploiting a new optimistic $Q$-function
estimator. Finally, we establish regret lower bounds in terms of data-dependent complexity measures for the
adversarial regime and a variance measure for the
stochastic regime, implying that the regret upper bounds achieved by the global-optimization approach are nearly optimal.
Read the full abstract ▾
Machine Learning
Correcting Boundary Bias and Observation Independence in Bayesian Experimental Design
Sanna Jarl, Jens Sjölund, Jonathan J. S. Scragg et al. (+1 more)
In many experimental settings, active learning can improve sample efficiency by sequentially selecting where to measure, which is particularly valuable when experiments are expensive. Gaussian processes with variance-based acquisition criteria are widely used for this purpose, but have two limitations. First, they are observation-independent: their posterior variance depends only on where samples are acquired, not on what is measured, impairing their sensitivity to the structure of the acquired data. Second, they inflate the variance near boundaries, leading to excessive sampling at the edges of the space compared to the interior. These limitations undermine the gains in sampling efficiency expected from sequential acquisition. We address both limitations. We derive a reconstruction-driven design density and use the posterior mean to build a training-free warp that places more measurements where the target function varies rapidly. A
geometric equalizer separately corrects boundary bias. Across sixteen synthetic and two real-data
benchmarks, the
geometric equalizer consistently improves function reconstruction by correcting boundary bias, while the reconstruction warp provides further gains by concentrating measurements where the posterior mean varies rapidly.
Read the full abstract ▾
All authors Sanna Jarl, Jens Sjölund, Jonathan J. S. Scragg, Maria Bånkestad
Machine Learning
Internal Flow Signatures for Self-Checking and Refinement in LLMs
Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa et al. (+3 more)
Large
language models can generate fluent answers that are unfaithful to the provided context, while many safeguards rely on external verification or a separate judge after generation. We introduce internal flow signatures that audit decision formation from depthwise dynamics at a fixed inter-block monitoring boundary. The method stabilizes
token-wise motion via bias-centered monitoring, then summarizes trajectories in compact moving readout-aligned subspaces constructed from the top
token and its close competitors within each depth window. Neighboring window frames are aligned by an orthogonal transport, yielding depth-comparable transported step lengths, turning angles, and subspace drift summaries that are invariant to within-window basis choices. A lightweight GRU validator trained on these signatures performs self-checking without modifying the base model. Beyond detection, the validator localizes a culprit depth event and enables a targeted refinement: the model rolls back to the culprit
token and clamps an abnormal transported step at the identified block while preserving the orthogonal residual. The resulting pipeline provides actionable localization and low-overhead self-checking from internal decision dynamics. Code is available at github.com/EavnJeong/Internal-Flow-Signatures-for-Self-Checking-and-Refinement-in-LLMs.
Read the full abstract ▾
All authors Sungheon Jeong, Sanggeon Yun, Ryozo Masukawa, Wenjun Haung, Hanning Chen, Mohsen Imani
Machine Learning · Cross-listed from cs.AI
Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova et al. (+1 more)
We present a
geometric framework for analysing multi-head
attention in large
language models (LLMs). Without altering the mechanism, we view standard
attention through a top-N selection lens and study its behaviour directly in value-state space. We define
geometric metrics - Precision, Recall, and F-score - to quantify separability between selected and non-selected
tokens, and derive non-asymptotic bounds with explicit dependence on dimension and margin under empirically motivated assumptions (stable value norms with a compressed sink
token, exponential similarity decay, and piecewise
attention weight profiles). The theory predicts a small-N operating regime of strongest non-trivial separability and clarifies how sequence length and sink similarity shape the metrics. Empirically, across LLaMA-2-7B, Gemma-7B, and Mistral-7B, measurements closely track the theoretical envelopes: top-N selection sharpens separability, sink similarity correlates with Recall. We also found that in LLaMA-2-7B heads specialize into three regimes - Retriever, Mixer, Reset - with distinct
geometric signatures. Overall,
attention behaves as a structured
geometric classifier with measurable criteria for
token selection, offering head level interpretability and informing geometry-aware sparsification and design of
attention in LLMs.
Read the full abstract ▾
All authors Timur Mudarisov, Mikhal Burtsev, Tatiana Petrova, Radu State
Machine Learning · Cross-listed from cs.AI
Shidong Yang, Tongwen Huang, Hao Wen et al. (+3 more)
Multimodal reward models are crucial for aligning
multimodal large
language models with human preferences. Recent works have incorporated
reasoning capabilities into these models, achieving promising results. However, training these models suffers from two critical challenges: (1) the inherent noise in preference
datasets, which degrades model performance, and (2) the inefficiency of conventional training methods, which ignore the differences in sample difficulty. In this paper, we identify a strong correlation between response
entropy and accuracy, indicating that
entropy can serve as a reliable and unsupervised proxy for annotation noise and sample difficulty. Based on this insight, we propose a novel
Entropy-Guided Training (EGT) approach for
multimodal reasoning reward models, which combines two strategies: (1)
entropy-guided data curation to mitigate the impact of unreliable samples, and (2) an
entropy-guided training strategy that progressively introduces more complex examples. Extensive experiments across three
benchmarks show that the EGT-trained model consistently outperforms state-of-the-art
multimodal reward models.
Read the full abstract ▾
All authors Shidong Yang, Tongwen Huang, Hao Wen, Yong Wang, Li Chen, Xiangxiang Chu
Machine Learning
Autocorrelated Optimize-via-Estimate: Predict-then-Optimize versus Finite-sample Optimal
Zichun Wang, Gar Goei Loke and Ruiting Zuo
Models that directly optimize for out-of-sample performance in the finite-sample regime have emerged as a promising alternative to traditional estimate-then-optimize approaches in data-driven optimization. In this work, we compare their performance in the context of autocorrelated uncertainties, specifically, under a Vector Autoregressive Moving Average VARMA(p,q) process. We propose an autocorrelated Optimize-via-Estimate (A-OVE) model that obtains an out-of-sample optimal solution as a function of sufficient statistics, and propose a recursive form for computing its sufficient statistics. We evaluate these models on a portfolio optimization problem with trading costs. A-OVE achieves low regret relative to a perfect information oracle, outperforming predict-then-optimize machine learning
benchmarks. Notably, machine learning models with higher accuracy can have poorer decision quality, echoing the growing literature in data-driven optimization. Performance is retained under small mis-specification.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Grappa: Gradient-Only Communication for Scalable Graph Neural Network Training
Chongyang Xu, Christoph Siebenbrunner and Laurent Bindschaedler
Cross-partition edges dominate the cost of distributed GNN training: fetching remote features and activations per iteration overwhelms the network as graphs deepen and partition counts grow. Grappa is a distributed GNN training framework that enforces gradient-only communication: during each iteration, partitions train in isolation and exchange only gradients for the global update. To recover accuracy lost to isolation, Grappa (i) periodically repartitions to expose new neighborhoods and (ii) applies a lightweight coverage-corrected gradient aggregation inspired by importance sampling. We present an asymptotically unbiased
estimator for gradient correction, which we use to develop a minimum-distance batch-level variant that is compatible with common deep-learning packages. We also introduce a shrinkage version that improves stability in practice. Empirical results on real and synthetic graphs show that Grappa trains GNNs 4x faster on average (up to 13x) than state-of-the-art systems, achieves better accuracy especially for deeper models, and sustains training at the trillion-edge scale on commodity hardware. Grappa is model-agnostic, supports full-graph and mini-batch training, and does not rely on high-bandwidth interconnects or caching.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Transformers as Measure-Theoretic Associative Memory: A Statistical Perspective and Minimax Optimality
Ryotaro Kawata and Taiji Suzuki
Transformers excel through content-addressable
retrieval and the ability to exploit contexts of, in principle, unbounded length. We recast associative
memory at the level of probability measures, treating a context as a distribution over
tokens and viewing
attention as an integral operator on measures. Concretely, for mixture contexts $\nu = I^{-1} \sum_{i=1}^I \mu^{(i^*)}$ and a query $x_{\mathrm{q}}(i^*)$, the task decomposes into (i) recall of the relevant component $\mu^{(i^*)}$ and (ii) prediction from $(\mu_{i^*},x_\mathrm{q})$. We study learned softmax
attention (not a frozen kernel) trained by empirical risk minimization and show that a shallow measure-theoretic
Transformer composed with an MLP learns the recall-and-predict map under a spectral assumption on the input densities. We further establish a matching minimax lower bound with the same rate exponent (up to multiplicative constants), proving sharpness of the convergence order. The framework offers a principled recipe for designing and analyzing
Transformers that recall from arbitrarily long, distributional contexts with provable generalization guarantees.
Read the full abstract ▾
Machine Learning · Cross-listed from eess.AS
RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responses
Shaoheng Xu, Chunyi Sun, Jihui Zhang et al. (+2 more)
Room impulse responses (RIRs) are essential for many acoustic signal processing tasks, yet measuring them densely across space is often impractical. In this work, we propose RIR-Former, a grid-free, one-step feed-forward model for RIR reconstruction. By introducing a sinusoidal encoding module into a
transformer backbone, our method effectively incorporates microphone position information, enabling interpolation at arbitrary array locations. Furthermore, a segmented multi-branch decoder is designed to separately handle early reflections and late reverberation, improving reconstruction across the entire RIR. Experiments on diverse simulated acoustic environments demonstrate that RIR-Former consistently outperforms state-of-the-art baselines in terms of normalized mean square error (NMSE) and cosine distance (CD), under varying missing rates and array configurations. These results highlight the potential of our approach for practical deployment and motivate future work on scaling from randomly spaced linear arrays to complex array geometries, dynamic acoustic scenes, and real-world environments.
Read the full abstract ▾
All authors Shaoheng Xu, Chunyi Sun, Jihui Zhang, Prasanga N. Samarasinghe, Thushara D. Abhayapala
Machine Learning
Time2Vec Transformer for Robust Gesture Recognition from Low-Density sEMG
Blagoj Hristov, Hristijan Gjoreski, Vesna Ojleska Latkoska et al. (+1 more)
Accurate and responsive myoelectric prosthesis control typically relies on complex, dense multi-sensor arrays, which limits consumer accessibility. This paper presents a novel, data-efficient deep learning framework designed to achieve precise and accurate control using minimal sensor hardware. Leveraging an external
dataset of 8 subjects, our approach implements a hybrid
Transformer optimized for sparse, two-channel surface electromyography (sEMG). Unlike standard architectures that use fixed positional encodings, we integrate Time2Vec learnable temporal
embeddings to capture the
stochastic temporal warping inherent in biological signals. Furthermore, we employ a normalized additive fusion strategy that aligns the latent distributions of spatial and temporal features, preventing the destructive interference common in standard implementations. A two-stage curriculum learning protocol is utilized to ensure robust feature extraction despite data scarcity. The proposed architecture achieves a state-of-the-art multi-subject F1-score of 95.7% $\pm$ 0.20% for a 10-class movement set, statistically outperforming both a standard
Transformer with fixed encodings and a recurrent CNN-LSTM model. Architectural optimization reveals that a balanced allocation of model capacity between spatial and temporal dimensions yields the highest stability. Furthermore, while direct transfer to a new unseen subject led to poor accuracy due to domain shifts, a rapid calibration protocol utilizing only two trials per gesture recovered performance from 21.0% $\pm$ 2.98% to 96.9% $\pm$ 0.52%. By validating that high-fidelity temporal
embeddings can compensate for low spatial resolution, this work challenges the necessity of high-density sensing. The proposed framework offers a robust, cost-effective blueprint for next-generation prosthetic interfaces capable of rapid personalization.
Read the full abstract ▾
All authors Blagoj Hristov, Hristijan Gjoreski, Vesna Ojleska Latkoska, Gorjan Nadzinski
Machine Learning
Designing Time Series Experiments in A/B Testing with Transformer Reinforcement Learning
Xiangkun Wu, Qianglin Wen, Yingying Zhang et al. (+3 more)
A/B testing has become a gold standard for modern technological companies to conduct policy evaluation. Yet, its application to time series experiments, where policies are sequentially assigned over time, remains challenging. Existing designs suffer from two limitations: (i) they do not fully leverage the entire history for treatment allocation; (ii) they rely on strong assumptions to approximate the objective function (e.g., the mean squared error of the estimated treatment effect) for optimizing the design. We first establish an impossibility
theorem showing that failure to condition on the full history leads to suboptimal designs, due to the dynamic dependencies in time series experiments. To address both limitations simultaneously, we next propose a
transformer reinforcement learning (RL) approach which leverages
transformers to condition allocation on the entire history and employs RL to directly optimize the MSE without relying on restrictive assumptions. Empirical evaluations on synthetic data, a publicly available dispatch simulator, and a real-world ridesharing
dataset demonstrate that our proposal consistently outperforms existing designs.
Read the full abstract ▾
All authors Xiangkun Wu, Qianglin Wen, Yingying Zhang, Hongtu Zhu, Ting Li, Chengchun Shi
Machine Learning
FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented Optimization
Zeyan Wang, Zhengmao Liu, Yongxin Cai et al. (+5 more)
Federated Unlearning (FU) aims to efficiently remove the influence of specific client data from a
federated model while preserving utility for the remaining clients. However, three key challenges remain: (1) existing unlearning objectives often compromise model utility or increase vulnerability to Membership Inference Attacks (MIA); (2) there is a persistent conflict between forgetting and utility, where further unlearning inevitably harms retained performance; and (3) support for concurrent multi-client unlearning is poor, as gradient conflicts among clients degrade the quality of forgetting. To address these issues, we propose FUPareto, an efficient unlearning framework via Pareto-augmented optimization. We first introduce the Minimum Boundary Shift (MBS) Loss, which enforces unlearning by suppressing the target class logit below the highest non-target class logit; this can improve the unlearning efficiency and mitigate MIA risks. During the unlearning process, FUPareto performs Pareto improvement steps to preserve model utility and executes Pareto expansion to guarantee forgetting. Specifically, during Pareto expansion, the framework integrates a Null-Space Projected Multiple Gradient Descent
Algorithm (MGDA) to decouple gradient conflicts. This enables effective, fair, and concurrent unlearning for multiple clients while minimizing utility degradation. Extensive experiments across diverse scenarios demonstrate that FUPareto consistently outperforms state-of-the-art FU methods in both unlearning efficacy and retained utility.
Read the full abstract ▾
All authors Zeyan Wang, Zhengmao Liu, Yongxin Cai, Chi Li, Xiaoying Tang, Jingchao Chen, Zibin Pan, Jing Qiu
Machine Learning
Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
Ziwei Luo, Ziqi Jin, Lei Wang et al. (+2 more)
This work presents self-rewarding sequential Monte Carlo (SMC), an inference-time scaling
algorithm enabling effective sampling of masked
diffusion language models (MDLMs). Our
algorithm stems from the observation that most existing MDLMs rely on a confidence-based sampling strategy, where only
tokens with the highest prediction confidence are preserved at each step. This restricts the generation to a noise-sensitive, greedy decoding paradigm, resulting in an inevitable collapse in the diversity of possible paths. We address this problem by launching multiple interacting
diffusion processes in parallel, referred to as particles, for trajectory exploration. Importantly, we introduce the trajectory-level confidence as a self-rewarding signal for assigning particle importance weights. During sampling, particles are iteratively weighted and resampled to systematically steer generation towards globally confident, high-quality samples. Our self-rewarding SMC is verified on various masked
diffusion language models and
benchmarks, achieving significant improvement without extra training or reward guidance, while effectively converting parallel inference capacity into improved sampling quality. Our code is available at https://github.com/Algolzw/self-rewarding-smc.
Read the full abstract ▾
All authors Ziwei Luo, Ziqi Jin, Lei Wang, Lidong Bing, Thomas B. Schön
Machine Learning
No Generation without Representation: Efficient Causal Protein Language Models Enable Zero-Shot Fitness Estimation
Furkan Eris
Protein language models (PLMs) face a fundamental divide: masked
language models (MLMs) excel at fitness prediction while causal models enable generation, forcing practitioners to maintain separate architectures. We introduce Proust, a 309M-parameter causal PLM that bridges this gap through architectural innovations adapted from recent LLM research, including grouped-query
attention with shared K/V projections, cross-layer value residuals, and depthwise causal convolutions. Trained on 33B
tokens in 40 B200 GPU-hours, Proust achieves Spearman $\rho = 0.390$ on ProteinGym substitutions, competitive with MLMs requiring 50–200$\times$ the compute. On indels, Proust sets a new state-of-the-art, outperforming models up to 20$\times$ larger. On EVEREST viral fitness
benchmarks, it approaches structure-aware methods using sequence alone. These powerful representations position Proust in a sweet spot as it also retains native generative capabilities that MLMs lack by design. Interpretability analysis reveals that per-position
entropy variance predicts, to an extent, when
retrieval augmentation helps and hurts. Such insights can grow in both quantity and quality at scale and inform capabilities such as test-time scaling. Code and weights are available at https://github.com/Furkan9015/proust-inference
Read the full abstract ▾
Machine Learning
Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models
Jinbin Bai, Yixuan Li, Yuchen Zhu et al. (+8 more)
Inference-time compute has re-emerged as a practical way to improve LLM
reasoning. Most test-time scaling (TTS)
algorithms rely on autoregressive decoding, which is ill-suited to discrete
diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose Prism (
Pruning, Remasking, and Integrated Self-verification Method), an efficient TTS framework for dLLMs that (i) performs Hierarchical Trajectory Search (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) introduces Local branching with partial remasking to explore diverse implementations while preserving high-confidence
tokens, and (iii) replaces external verifiers with Self-Verified Feedback (SVF) obtained via self-evaluation
prompts on intermediate completions. Across four mathematical
reasoning and code generation
benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our Prism achieves a favorable performance-efficiency trade-off, matching best-of-N performance with substantially fewer function evaluations (NFE). The code is released at https://github.com/viiika/Prism.
Read the full abstract ▾
All authors Jinbin Bai, Yixuan Li, Yuchen Zhu, Yi Xin, Qingyu Shi, Aosong Feng, Xiaohong Liu, Molei Tao, Jianru Xue, Xiangtai Li, Ming-Hsuan Yang
Machine Learning
DOGMA: Weaving Structural Information into Data-centric Single-cell Transcriptomics Analysis
Ru Zhang, Xunkai Li, Yaxin Deng et al. (+7 more)
Recently, data-centric AI methodology has been a dominant paradigm in single-
cell transcriptomics analysis, which treats data representation rather than model complexity as the fundamental bottleneck. In the review of current studies, earlier sequence methods treat
cells as independent entities and adapt prevalent ML models to analyze their directly inherited sequence data. Despite their simplicity and intuition, these methods overlook the latent intercellular relationships driven by the functional mechanisms of biological systems and the inherent quality issues of the raw sequencing data. Therefore, a series of structured methods has emerged. Although they employ various heuristic rules to capture intricate intercellular relationships and enhance the raw sequencing data, these methods often neglect biological prior knowledge. This omission incurs substantial overhead and yields suboptimal graph representations, hindering the utility of ML models. To address these issues, we propose DOGMA, a data-centric framework designed for the structural reshaping and semantic enhancement of raw data through multi-level biological prior knowledge. Transcending reliance on purely data-driven heuristics, DOGMA provides a prior-guided graph construction pipeline that integrates statistical
alignment with
Cell Ontology and phylogenetic structure for biologically grounded
cell-graph construction and robust cross-species
alignment. Furthermore, Gene Ontology is utilized to bridge the feature-level semantic gap by incorporating functional priors. In complex multi-species and multi-organ
benchmarks, DOGMA exhibits strong robustness in strict zero-shot
cell-type evaluation and sample efficiency while using substantially lower GPU
memory and inference time in downstream evaluation.
Read the full abstract ▾
All authors Ru Zhang, Xunkai Li, Yaxin Deng, Sicheng Liu, Daohan Su, Qiangqiang Dai, Hongchao Qin, Rong-Hua Li, Guoren Wang, Jia Li
Machine Learning
Hyperbolic Graph Neural Networks Under the Microscope: The Role of Geometry-Task Alignment
Dionisia Naddeo, Jonas Linkerhägner, Nicola Toschi et al. (+2 more)
Many complex networks exhibit hierarchical, tree-like structures, making
hyperbolic space a natural candidate wherein to learn representations of them. Based on this observation,
Hyperbolic Graph Neural Networks (HGNNs) have been widely adopted as a principled choice for representation learning on tree-like graphs. In this work, we question this paradigm by proposing the additional condition of geometry–task
alignment, i.e., whether the metric structure of the target follows that of the input graph. We start by empirically showing that HGNNs can recover low-distortion representations when supervision explicitly rewards metric preservation and proceed by theoretically analyzing a controlled regression setting in which a linear readout benefits from representations whose geometry is aligned with the target metric. Finally, by relying on both predictive performance and
embedding distortion, we further show that HGNNs gain an advantage on link prediction, a naturally geometry-aligned task, whereas this advantage largely disappears on standard node classification
benchmarks. Overall, our findings shift the focus from only asking "Is the graph
hyperbolic?" to also questioning "Is the task aligned with
hyperbolic geometry?", showing that HGNNs consistently outperform Euclidean models under such
alignment, while their advantage vanishes otherwise.
Read the full abstract ▾
All authors Dionisia Naddeo, Jonas Linkerhägner, Nicola Toschi, Geri Skenderi, Veronica Lachi
Machine Learning
Beyond Precision: Training-Inference Mismatch is an Optimization Problem and Simple LR Scheduling Fixes It
Yaxiang Zhang, Yingru Li, Jiacai Liu et al. (+4 more)
Reinforcement Learning (RL) for training Large
Language Models is notoriously unstable. While recent studies attribute this to "training inference mismatch stemming" from inconsistent hybrid engines, standard remedies, such as Importance Sampling, might fail during extended training runs. In this work, we analyze this instability through the lens of optimization, demonstrating that gradient noise and training-inference mismatch escalate in tandem as training progresses. Meanwhile, we find that the mismatch can be effectively suppressed by shrinking the update size. Taken together, we deduce that the mismatch is not merely a static numerical discrepancy, but a dynamic failure coupled with the model's optimization. Based on this insight, we propose a simple yet effective solution: a specialized Learning Rate (LR) scheduler. Instead of pre-defined decay schedule in traditional LR scheduler, our method dynamically triggers LR decay based on response length, which we identify as a reliable early-warning signal for impending instability. Empirical evidence suggests that by reducing the learning rate as gradient noise rises, we can consistently stabilize RL training and keep the training-inference mismatch at a safe level.
Read the full abstract ▾
All authors Yaxiang Zhang, Yingru Li, Jiacai Liu, Jiawei Xu, Ziniu Li, Qian Liu, Haoyuan Li
Machine Learning · Cross-listed from stat.ME
Learning Sequential Decisions from Multiple Sources via Group-Robust Markov Decision Processes
Mingyuan Xu, Zongqi Xia, Tianxi Cai et al. (+2 more)
Learning a common policy from multiple source environments requires accounting for cross-source heterogeneity, and the offline setting introduces an additional challenge of limited data coverage. We formulate this problem as a distributionally robust Markov decision process under a shared linear MDP representation with source-specific transition and reward components. The uncertainty set is constructed through feature-wise mixtures of these components, yielding a $d$-rectangular structure that captures cross-source heterogeneity and admits a robust Bellman recursion. Building on this formulation, we develop Group-Robust Pessimistic Value Iteration (GR-PEVI), an offline policy-learning
algorithm that combines feature-wise worst-case aggregation with a data-dependent pessimism penalty. Under a robust partial coverage condition, we establish finite-sample suboptimality guarantees for GR-PEVI and extend the analysis to clustered sources, characterizing the trade-off between the statistical gain from pooling similar sources and the approximation error induced by within-cluster heterogeneity. Simulation studies demonstrate the effectiveness of GR-PEVI, with empirical behavior consistent with the theoretical analysis. We apply GR-PEVI to a multi-source electronic health record study of multiple sclerosis treatment decisions to illustrate its use in a clinical setting.
Read the full abstract ▾
All authors Mingyuan Xu, Zongqi Xia, Tianxi Cai, Doudou Zhou, Nian Si
Machine Learning · Cross-listed from cs.CL
Sentence Curve Language Models
DongNyeong Heo, Taehwan Kim and Heeyoul Choi
Language models (LMs) are a central component of modern AI systems, and
diffusion language models (DLMs) have recently emerged as a competitive alternative. Both paradigms rely on word
embeddings not only to represent the input sentence, but also to represent the target sentence that backbone models are trained to predict. We argue that such static
embedding of the target word is insensitive to neighboring words, encouraging locally accurate word prediction while global sentence structure is less emphasized. To address this, we propose a continuous sentence representation, termed sentence curve, defined as a spline curve whose control points affect multiple words in the sentence. Based on this representation, we introduce sentence curve
language model (SCLM), which extends DLMs to predict sentence curves instead of the static word
embeddings. We theoretically show that sentence curve prediction induces a regularization effect that promotes global structure modeling, and characterize how different sentence curve types affect this behavior. Empirically, SCLM achieves state-of-the-art performance among DLMs on IWSLT14 and WMT14, shows stable training without burdensome knowledge
distillation, and demonstrates promising potential compared to discrete DLMs on LM1B.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Ido Faran, Nathan S. Netanyahu and Maxim Shoshany
Long-term satellite image time series (SITS) analysis in heterogeneous landscapes faces significant challenges, particularly in Mediterranean regions where complex spatial patterns, seasonal variations, and multi-decade environmental changes interact across different scales. This paper presents the Spatio-Temporal
Transformer for Long Term
Forecasting (STT-LTF ), an extended framework that advances beyond purely temporal analysis to integrate spatial context modeling with temporal sequence prediction. STT-LTF processes multi-scale spatial patches alongside temporal sequences (up to 20 years) through a unified
transformer architecture, capturing both local neighborhood relationships and regional
climate influences. The framework employs comprehensive self-supervised learning with spatial masking, temporal masking, and horizon sampling strategies, enabling robust model training from 40 years of unlabeled Landsat imagery. Unlike autoregressive approaches, STT-LTF directly predicts arbitrary future time points without error accumulation, incorporating spatial patch
embeddings, cyclical temporal encoding, and geographic coordinates to learn complex dependencies across heterogeneous Mediterranean ecosystems. Experimental evaluation on Landsat data (1984-2024) demonstrates that STT-LTF achieves a Mean Absolute Error (MAE) of 0.0328 and R^2 of 0.8412 for next-year predictions, outperforming traditional statistical methods, CNN-based approaches, LSTM networks, and standard
transformers. The framework's ability to handle irregular temporal sampling and variable prediction horizons makes it particularly suitable for analysis of heterogeneous landscapes experiencing rapid ecological transitions.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
Mingrui Liu, Sixiao Zhang, Cheng Long et al. (+1 more)
Large
Language Models (LLMs) are increasingly vulnerable to
Prompt Injection (PI) attacks, where
adversarial instructions hidden within retrieved contexts hijack the model's execution flow. Current defenses typically face a critical trade-off: prevention-based fine-tuning often degrades general utility via the "
alignment tax", while detection-based filtering incurs prohibitive latency and
memory costs. To bridge this gap, we propose RedVisor, a unified framework that synthesizes the explainability of detection systems with the seamless integration of prevention strategies. To the best of our knowledge, RedVisor is the first approach to leverage fine-grained
reasoning paths to simultaneously detect attacks and guide the model's safe response. We implement this via a lightweight, removable adapter positioned atop the frozen backbone. This adapter serves a dual function: it first generates an explainable analysis that precisely localizes the injection and articulates the threat, which then explicitly conditions the model to reject the malicious command. Uniquely, the adapter is active only during this
reasoning phase and is effectively muted during the subsequent response generation. This architecture yields two distinct advantages: (1) it mathematically preserves the backbone's original utility on benign inputs; and (2) it enables a novel KV Cache Reuse strategy, eliminating the redundant prefill computation inherent to decoupled pipelines. We further pioneer the integration of this defense into the vLLM serving engine with custom kernels. Experiments demonstrate that RedVisor outperforms state-of-the-art defenses in detection accuracy and throughput while incurring negligible utility loss.
Read the full abstract ▾
All authors Mingrui Liu, Sixiao Zhang, Cheng Long, Kwok-Yan Lam
Machine Learning
Grad2Reward: From Sparse Judgment to Dense Rewards for Improving Open-Ended LLM Reasoning
Zheng Zhang, Ao Lu, Yuanhao Zeng et al. (+5 more)
Reinforcement Learning with Verifiable Rewards (RLVR) has catalyzed significant breakthroughs in complex LLM
reasoning within verifiable domains, such as mathematics and programming. Recent efforts have sought to extend this paradigm to open-ended tasks by employing LLMs-as-a-Judge to provide sequence-level rewards for policy optimization. However, these rewards are inherently sparse, failing to provide the fine-grained supervision necessary for generating complex, long-form trajectories. Furthermore, current work treats the Judge as a black-box oracle, discarding the rich intermediate feedback signals encoded in it. To address these limitations, we introduce Grad2Reward, a novel framework that extracts dense process rewards directly from the Judge's model inference process via a single backward pass. By leveraging gradient-based attribution, Grad2Reward enables precise
token-level credit assignment, substantially enhancing training efficiency and
reasoning quality. Additionally, Grad2Reward introduces a self-judging mechanism, allowing the policy to improve through its own evaluative signals without training specialized reward models or reliance on superior external Judges. The experiments demonstrate that policies optimized with Grad2Reward achieve outstanding performance across diverse open-ended tasks, affirming its effectiveness and broad generalizability.
Read the full abstract ▾
All authors Zheng Zhang, Ao Lu, Yuanhao Zeng, Ziwei Shan, Jinjin Guo, Lufei Li, Yexin Li, Kan Ren
Machine Learning
Stein-Rule Shrinkage for Stochastic Gradient Estimation in High Dimensions
M. Arashi and M. Amintoosi
Stochastic gradient methods are central to large-scale learning, but they treat mini-batch gradients as unbiased
estimators, which classical decision theory shows are inadmissible in high dimensions. We formulate gradient computation as a high-dimensional estimation problem and introduce a framework based on Stein-rule shrinkage. We construct a gradient
estimator that adaptively contracts noisy mini-batch gradients toward a stable
estimator derived from historical momentum. The shrinkage intensity is determined in a data-driven manner using an online estimate of gradient noise variance, leveraging statistics from adaptive optimizers. Under a Gaussian noise model, we show our
estimator uniformly dominates the standard
stochastic gradient under squared error loss and is minimax-optimal. We incorporate this into the Adam optimizer, yielding SR-Adam, a practical
algorithm with negligible computational cost. Empirical evaluations on CIFAR10 and CIFAR100 across multiple levels of input noise show consistent improvements over Adam in the large-batch regime. Ablation studies indicate that gains arise primarily from selectively applying shrinkage to high-dimensional convolutional layers, while indiscriminate shrinkage across all parameters degrades performance. These results illustrate that classical shrinkage principles provide a principled approach to improving
stochastic gradient estimation in deep learning.
Read the full abstract ▾
Machine Learning
Position: Beyond Model-Centric Prediction – Agentic Time Series Forecasting
Mingyue Cheng, Xiaoyu Tao, Qi Liu et al. (+2 more)
Time series
forecasting has traditionally been formulated as a model-centric, static, and single-pass prediction problem that maps historical observations to future values. While this paradigm has driven substantial progress, it proves insufficient in adaptive and multi-turn settings where
forecasting requires informative feature extraction,
reasoning-driven inference, iterative refinement, and continual adaptation over time. In this paper, we argue for agentic time series
forecasting (ATSF), which reframes
forecasting as an agentic process composed of perception, planning, action, reflection, and
memory. Rather than focusing solely on predictive models, ATSF emphasizes organizing
forecasting as an agentic workflow that can interact with tools, incorporate feedback from outcomes, and evolve through experience accumulation. We outline three representative implementation paradigms – workflow-based design, agentic reinforcement learning, and a hybrid agentic workflow paradigm – and discuss the opportunities and challenges that arise when shifting from model-centric prediction to agentic
forecasting. Together, this position aims to establish agentic
forecasting as a foundation for future research at the intersection of time series
forecasting.
Read the full abstract ▾
All authors Mingyue Cheng, Xiaoyu Tao, Qi Liu, Ze Guo, Enhong Chen
Machine Learning · Cross-listed from cs.AI
Efficient Cross-Architecture Knowledge Transfer for Large-Scale Online User Response Prediction
Yucheng Wu, Yuekui Yang, Hongzheng Li et al. (+6 more)
Deploying new architectures in large-scale user response prediction systems incurs high model switching costs due to expensive retraining on massive historical data and performance degradation under data retention constraints. Existing knowledge
distillation methods struggle with architectural heterogeneity and the prohibitive cost of transferring large
embedding tables. We propose CrossAdapt, a two-stage framework for efficient cross-architecture knowledge transfer. The offline stage enables rapid
embedding transfer via dimension-adaptive projections without iterative training, combined with progressive network
distillation and strategic sampling to reduce computational cost. The online stage introduces asymmetric co-
distillation, where students update frequently while teachers update infrequently, together with a distribution-aware adaptation mechanism that dynamically balances historical knowledge preservation and fast adaptation to evolving data. Experiments on three public
datasets show that CrossAdapt achieves 0.27-0.43% AUC improvements while reducing training time by 43-71%. Large-scale deployment on Tencent WeChat Channels (~10M daily samples) further demonstrates its effectiveness, significantly mitigating AUC degradation, LogLoss increase, and prediction bias compared to standard
distillation baselines.
Read the full abstract ▾
All authors Yucheng Wu, Yuekui Yang, Hongzheng Li, Anan Liu, Jian Xiao, Junjie Zhai, Huan Yu, Shaoping Ma, Leye Wang
Machine Learning · Cross-listed from cs.HC
Cost-Aware Bayesian Optimization for Prototyping Interactive Devices
Thomas Langerak, Renate Zhang, Ziyuan Wang et al. (+2 more)
Deciding which idea is worth prototyping is a central concern in iterative design. A prototype should be produced when the expected improvement is high and the cost is low. However, this is hard to decide, because costs can vary drastically: a simple parameter tweak may take seconds, while fabricating hardware consumes material and energy. Such asymmetries, can discourage a designer from exploring the design space. In this paper, we present an extension of cost-aware
Bayesian optimization to account for diverse prototyping costs. The method builds on the power of
Bayesian optimization and requires only a minimal modification to the acquisition function. The key idea is to use designer-estimated costs to guide sampling toward more cost-effective prototypes. In technical evaluations, the method achieved comparable utility to a cost-agnostic baseline while requiring only ${\approx}70\%$ of the cost; under strict budgets, it outperformed the baseline threefold. A within-subjects study with 12 participants in a realistic joystick design task demonstrated similar benefits. These results show that accounting for prototyping costs can make
Bayesian optimization more compatible with real-world design projects.
Read the full abstract ▾
All authors Thomas Langerak, Renate Zhang, Ziyuan Wang, Per Ola Kristensson, Antti Oulasvirta