Machine Learning · Cross-listed from cs.CV
Reliable Mislabel Detection for Video Capsule Endoscopy Data
Julia Werner, Julius Oexle, Oliver Bause et al. (+5 more)
The classification performance of deep neural networks relies strongly on access to large, accurately annotated
datasets. In medical imaging, however, obtaining such
datasets is particularly challenging since annotations must be provided by specialized physicians, which severely limits the pool of annotators. Furthermore, class boundaries can often be ambiguous or difficult to define which further complicates machine learning-based classification. In this paper, we want to address this problem and introduce a framework for mislabel detection in medical
datasets. This is validated on the two largest, publicly available
datasets for
Video Capsule Endoscopy, an important imaging procedure for examining the gastrointestinal tract based on a
video stream of lowresolution images. In addition, potentially mislabeled samples identified by our pipeline were reviewed and re-annotated by three experienced gastroenterologists. Our results show that the proposed framework successfully detects incorrectly labeled data and results in an improved anomaly detection performance after cleaning the
datasets compared to current baselines.
Read the full abstract ▾
All authors Julia Werner, Julius Oexle, Oliver Bause, Maxime Le Floch, Franz Brinkmann, Hannah Tolle, Jochen Hampe, Oliver Bringmann
Machine Learning · Cross-listed from cs.SD
Reciprocal Latent Fields for Precomputed Sound Propagation
Hugo Seuté, Pranai Vasudev, Etienne Richan et al. (+1 more)
Realistic sound propagation is essential for immersion in a virtual scene, yet physically accurate wave-based simulations remain computationally prohibitive for real-time applications. Wave coding methods address this limitation by precomputing and compressing impulse responses of a given scene into a set of scalar acoustic parameters, which can reach unmanageable sizes in large environments with many source-receiver pairs. We introduce Reciprocal Latent Fields (RLF), a
memory-efficient framework for encoding and predicting these acoustic parameters. The RLF framework employs a volumetric grid of trainable latent
embeddings decoded with a symmetric function, ensuring acoustic reciprocity. We study a variety of decoders and show that leveraging Riemannian metric learning leads to a better reproduction of acoustic phenomena in complex scenes. Experimental validation demonstrates that RLF maintains replication quality while reducing the
memory footprint by several orders of magnitude. Furthermore, a MUSHRA-like subjective listening test indicates that sound rendered via RLF is perceptually indistinguishable from ground-truth simulations.
Read the full abstract ▾
All authors Hugo Seuté, Pranai Vasudev, Etienne Richan, Louis-Xavier Buffoni
Machine Learning
When RL Meets Adaptive Speculative Training: A Unified Training-Serving System
Junxiong Wang, Fengxiang Bie, Jisen Li et al. (+14 more)
Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled formulation introduces substantial deployment and adaptation lag: (1) high time-to-serve, since a speculator must be trained offline for a considerable period before deployment; (2) delayed utility feedback, since the true end-to-end decoding speedup is only known after training and cannot be inferred reliably from acceptance rate alone due to model-architecture and system-level overheads; and (3) domain-drift degradation, as the target model is repurposed to new domains and the speculator becomes stale and less effective. To address these issues, we present Aurora, a unified training-serving system that closes the loop by continuously learning a speculator directly from live inference traces. Aurora reframes online speculator learning as an asynchronous reinforcement-learning problem: accepted
tokens provide positive feedback, while rejected speculator proposals provide implicit negative feedback that we exploit to improve sample efficiency. Our design integrates an SGLang-based inference server with an asynchronous training server, enabling hot-swapped speculator updates without service interruption. Crucially, Aurora supports day-0 deployment: a speculator can be served immediately and rapidly adapted to live traffic, improving system performance while providing immediate utility feedback. Across experiments, Aurora achieves a 1.5x day-0 speedup on recently released frontier models (e.g., MiniMax M2.1 229B and Qwen3-Coder-Next 80B). Aurora also adapts effectively to distribution shifts in user traffic, delivering an additional 1.25x speedup over a well-trained but static speculator on widely used models (e.g., Qwen3 and Llama3).
Read the full abstract ▾
All authors Junxiong Wang, Fengxiang Bie, Jisen Li, Zhongzhu Zhou, Zelei Shao, Yubo Wang, Yinghui Liu, Qingyang Wu, Avner May, Sri Yanamandra, Ce Zhang, Tri Dao, Percy Liang, Ben Athiwaratkun, Shuaiwen Leon Song, Chenfeng Xu, Xiaoxia Wu
Machine Learning
Continuous-time reinforcement learning: ellipticity enables model-free value function approximation
Wenlong Mou
We study off-policy reinforcement learning for controlling continuous-time Markov
diffusion processes with discrete-time observations and actions. We consider model-free
algorithms with function approximation that learn value and advantage functions directly from data, without unrealistic structural assumptions on the dynamics. Leveraging the ellipticity of the
diffusions, we establish a new class of
Hilbert-space positive definiteness and boundedness properties for the Bellman operators. Based on these properties, we propose the Sobolev-prox fitted $q$-learning
algorithm, which learns value and advantage functions by iteratively solving least-squares regression problems. We derive oracle inequalities for the estimation error, governed by (i) the best approximation error of the function classes, (ii) their localized complexity, (iii) exponentially decaying optimization error, and (iv) numerical discretization error. These results identify ellipticity as a key structural property that renders reinforcement learning with function approximation for Markov
diffusions no harder than supervised learning.
Read the full abstract ▾
Machine Learning
Rank-Constrained Adaptation for Reliable Real-World Performance
Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi et al. (+2 more)
Deep learning models trained to optimize average accuracy often exhibit systematic failures on particular subpopulations. In real-world settings like healthcare, the subpopulations most affected by such disparities are frequently unlabeled, partially observed, or not known in advance. Existing group-robust methods typically assume prior knowledge of the relevant subgroups, using group annotations for training, validation, or model selection. We propose Misclassification Aware Rank-Limited Adaptation (MARLA), a parameter-efficient method for improving worst group performance without explicit subgroup annotations. MARLA leverages an ERM-trained model by calculating the model's misclassification probability scores on a held-out adaptation set to identify a low-dimensional subspace where errors concentrate. We then learn a rank-restricted additive correction to the classifier logits within that subspace. Across seven real-world
datasets, we evaluate group robustness under three settings: no knowledge of subgroup relevance, partial knowledge of subgroup relevance, and full knowledge of subgroup relevance. MARLA improves worst-group performance while remaining fast and parameter-efficient, with data-guided hyperparameter selection.
Read the full abstract ▾
All authors Abinitha Gourabathina, Hyewon Jeong, Teya Bergamaschi, Marzyeh Ghassemi, Collin Stultz
Machine Learning
From Kepler to Newton: Inductive Biases Guide Learned World Models in Transformers
Ziming Liu, Sophia Sanborn, Surya Ganguli et al. (+1 more)
Can general-purpose AI architectures go beyond prediction to discover the physical laws governing the universe? True intelligence relies on "world models" – causal abstractions that allow an
agent to not only predict future states but understand the underlying governing dynamics. While previous "AI Physicist" approaches have successfully recovered such laws, they typically rely on strong, domain-specific priors that effectively "bake in" the physics. Conversely, Vafa et al. recently showed that generic
Transformers fail to acquire these world models, achieving high predictive accuracy without capturing the underlying physical laws. We bridge this gap by systematically introducing three minimal inductive biases. We show that ensuring spatial smoothness (by formulating prediction as continuous regression) and stability (by training with noisy contexts to mitigate error accumulation) enables generic
Transformers to surpass prior failures and learn a coherent Keplerian world model, successfully fitting ellipses to planetary trajectories. However, true physical insight requires a third bias: temporal locality. By restricting the
attention window to the immediate past – imposing the simple assumption that future states depend only on the local state rather than a complex history – we force the model to abandon curve-fitting and discover Newtonian force representations. Our results demonstrate that simple architectural choices determine whether an AI becomes a curve-fitter or a physicist, marking a critical step toward automated scientific discovery.
Read the full abstract ▾
All authors Ziming Liu, Sophia Sanborn, Surya Ganguli, Andreas Tolias
Machine Learning · Cross-listed from eess.AS
Automatic Detection and Analysis of Singing Mistakes for Music Pedagogy
Sumit Kumar, Suraj Jaiswal, Parampreet Singh et al. (+1 more)
The advancement of machine learning in audio analysis has opened new possibilities for technology-enhanced music education. This paper introduces a framework for automatic singing mistake detection in the context of music pedagogy, supported by a newly curated
dataset. The
dataset comprises synchronized teacher learner vocal recordings, with annotations marking different types of mistakes made by learners. Using this
dataset, we develop different deep learning models for mistake detection and
benchmark them. To compare the efficacy of mistake detection systems, a new evaluation methodology is proposed. Experiments indicate that the proposed learning-based methods are superior to rule-based methods. A systematic study of errors and a cross-teacher study reveal insights into music pedagogy that can be utilised for various music applications. This work sets out new directions of research in music pedagogy. The codes and
dataset are publicly available.
Read the full abstract ▾
All authors Sumit Kumar, Suraj Jaiswal, Parampreet Singh, Vipul Arora
Machine Learning
Revisiting the Generic Transformer: Deconstructing a Strong Baseline for Time Series Foundation Models
Yunshi Wen, Wesley M. Gifford, Chandra Reddy et al. (+3 more)
The recent surge of interest in Time Series Foundation Models has rapidly advanced the field. Yet, heterogeneous training setups across studies make it difficult to determine whether performance improvements came from architectural innovations or effective data engineering. In this work, we investigate whether a standard patch
Transformer architecture, paired with a straightforward training protocol, can match the zero-shot
forecasting performance of state-of-the-art TSFMs. We conduct a comprehensive ablation study covering model scaling, data composition, and training techniques to examine the ingredients behind this performance. Our findings show that pretraining data composition, contiguous patch masking, and context length have a substantial effect on
forecasting accuracy, and that the generic architecture itself can deliver high performance with good scalability. By strictly controlling these experimental variables, we provide comprehensive empirical results on model scaling across multiple dimensions. Furthermore, we establish that the effectiveness of this training protocol generalizes robustly across
benchmarks and alternative architectures. We release our pretrained models and document the detailed training protocol and findings to establish a transparent, reproducible baseline for future research.
Read the full abstract ▾
All authors Yunshi Wen, Wesley M. Gifford, Chandra Reddy, Lam M. Nguyen, Jayant Kalagnanam, Anak Agung Julius
Machine Learning
A first realization of reinforcement learning-based closed-loop EEG-TMS
Dania Humaidan, Jiahua Xu, Jing Chen et al. (+8 more)
Background: Transcranial
magnetic stimulation (TMS) is a powerful tool to investigate neurophysiology of the human
brain and treat
brain disorders. Traditionally, therapeutic TMS has been applied in a one-size-fits-all approach, disregarding inter- and intra-individual differences.
Brain state-dependent
EEG-TMS, such as coupling TMS with a pre-specified phase of the sensorimotor mu-rhythm, enables the induction of differential neuroplastic effects depending on the targeted phase. But this approach is still user-dependent as it requires defining an a-priori target phase. Objectives: To present a first realization of a machine-learning-based, closed-loop real-time
EEG-TMS setup to identify user-independently the individual mu-rhythm phase associated with high- vs. low-corticospinal excitability states. Methods: We applied
EEG-TMS to 25 participants targeting the supplementary motor area-primary motor cortex network and used a reinforcement learning
algorithm to identify the mu-rhythm phase associated with high- vs. low corticospinal excitability. We employed linear mixed effects models and
Bayesian analysis to determine effects of reinforced learning on corticospinal excitability indexed by motor evoked potential amplitude, and functional connectivity indexed by the imaginary part of resting-state
EEG coherence. Results: Reinforcement learning effectively identified the mu-rhythm phase associated with high- vs. low-excitability states, and their repetitive stimulation resulted in long-term increases vs. decreases in functional connectivity in the stimulated sensorimotor network. Conclusions: We demonstrated for the first time the feasibility of closed-loop
EEG-TMS in humans, a critical step towards individualized treatment of
brain disorders.
Read the full abstract ▾
All authors Dania Humaidan, Jiahua Xu, Jing Chen, Christoph Zrenner, David Emanuel Vetter, Laura Marzetti, Paolo Belardinelli, Timo Roine, Risto J. Ilmoniemi, Gian Luca Romani, Ulf Zieman
Machine Learning
Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory
Hao Qiu, Andrew Jacobsen, Emmanuel Esposito et al. (+1 more)
In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standard setting by allowing the movement cost coefficients $\lambda_t$ to vary arbitrarily over time. Our main contribution is a novel
algorithm that establishes the first comparator-adaptive dynamic regret bound for this setting, guaranteeing $\widetilde{\mathcal{O}}(\sqrt{(M^2+MP_T)(T+\sum_t \lambda_t)})$ regret, where $P_T$ is the path length of the comparator sequence over $T$ rounds and $M$ is the maximal comparator norm. Our result recovers the optimal adaptive rates for both static and dynamic regret in OCO as the special case where $\lambda_t=0$ for all rounds. To demonstrate the versatility of our results, we consider two applications: OCO with delayed feedback and OCO with time-varying
memory. We show that both problems can be translated into time-varying movement costs, establishing a novel reduction specifically for the delayed feedback setting that is of independent interest. A crucial observation is that the first-order dependence on movement costs in our regret bound plays a key role in enabling optimal comparator-adaptive dynamic regret guarantees in both settings.
Read the full abstract ▾
All authors Hao Qiu, Andrew Jacobsen, Emmanuel Esposito, Mengxiao Zhang
Machine Learning
Supercharging Simulation-Based Inference for Bayesian Optimal Experimental Design
Samuel Klein, Willie Neiswanger, Daniel Ratner et al. (+2 more)
Bayesian optimal experimental design (BOED) seeks to maximize the expected information gain (EIG) of experiments. This requires a likelihood estimate, which in many settings is intractable. Simulation-based inference (SBI) provides powerful tools for this regime. However, existing work explicitly connecting SBI and BOED is restricted to a single contrastive EIG bound. We show that the EIG admits multiple formulations which can directly leverage modern SBI density
estimators, encompassing neural posterior, likelihood, and ratio estimation. Building on this perspective, we define a novel EIG
estimator using neural likelihood estimation. Further, we identify optimization as a key bottleneck of gradient based EIG maximization and show that a simple multi-start parallel gradient ascent procedure can substantially improve reliability and performance. With these innovations, our SBI-based BOED methods are able to match or outperform by up to $22\%$ existing state-of-the-art approaches across standard BOED
benchmarks.
Read the full abstract ▾
All authors Samuel Klein, Willie Neiswanger, Daniel Ratner, Michael Kagan, Sean Gasiorowski
Machine Learning
Sample Complexity of Causal Identification with Temporal Heterogeneity
Ameya Rathod, Sujay Belsare, Salvik Krishna Nautiyal et al. (+2 more)
Recovering a unique causal graph from observational data is an ill-posed problem because multiple generating mechanisms can lead to the same observational distribution. This problem becomes solvable only by exploiting specific structural or distributional assumptions. While recent work has separately utilized time-series dynamics or multi-environment heterogeneity to constrain this problem, we integrate both as complementary sources of heterogeneity. This integration yields unified necessary identifiability conditions and enables a rigorous analysis of the statistical limits of recovery under thin versus heavy-tailed noise. In particular, temporal structure is shown to effectively substitute for missing environmental diversity, possibly achieving identifiability even under insufficient heterogeneity. Extending this analysis to heavy-tailed (Student's t) distributions, we demonstrate that while
geometric identifiability conditions remain invariant, the sample complexity diverges significantly from the Gaussian baseline. Explicit information-theoretic bounds quantify this cost of robustness, establishing the fundamental limits of covariance-based causal graph recovery methods in realistic non-stationary systems. This work shifts the focus from whether causal structure is identifiable to whether it is statistically recoverable in practice.
Read the full abstract ▾
All authors Ameya Rathod, Sujay Belsare, Salvik Krishna Nautiyal, Dhruv Laad, Ponnurangam Kumaraguru
Machine Learning
A Cycle-Consistent Graph Surrogate for Full-Cycle Left Ventricular Myocardial Biomechanics
Siyu Mu, Wei Xuan Chan and Choon Hwai Yap
Image-based patient-specific simulation of left ventricular (LV) mechanics is valuable for understanding cardiac function and supporting clinical intervention planning, but conventional finite-element analysis (FEA) is computationally intensive. Current graph-based surrogates do not have full-cycle prediction capabilities, and physics-informed neural networks often struggle to converge on complex cardiac geometries. We present CardioGraphFENet (CGFENet), a unified graph-based surrogate for rapid full-cycle estimation of LV myocardial biomechanics, supervised by a large FEA simulation
dataset. The proposed model integrates (i) a global–local graph encoder to capture mesh features with weak-form-inspired global coupling, (ii) a gated recurrent unit-based temporal encoder conditioned on the target volume-time signal to model cycle-coherent dynamics, and (iii) a cycle-consistent bidirectional formulation for both loading and inverse unloading within a single framework. These strategies enable high fidelity with respect to traditional FEA ground truths and produce physiologically plausible pressure-volume loops that match FEA results when coupled with a lumped-parameter model. In particular, the cycle-consistency strategy enables a significant reduction in FEA supervision with only minimal loss in accuracy.
Read the full abstract ▾
Machine Learning
Vision Transformer Finetuning Benefits from Non-Smooth Components
Ambroise Odonnat, Laetitia Chapel, Romain Tavenard et al. (+1 more)
The smoothness of the
transformer architecture has been extensively studied in the context of generalization, training stability, and
adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper, we analyze the ability of
vision transformer components to adapt their outputs to changes in inputs, or, in other words, their plasticity. Defined as an average rate of change, it captures the sensitivity to input perturbation; in particular, a high plasticity implies a low smoothness. Our theoretical analysis and extensive experiments – over $1,000$ finetuning runs on large-scale
vision transformers – showcase that this perspective provides principled guidance in choosing the components to prioritize during adaptation. A key takeaway for practitioners is that the high plasticity of the
attention modules and feedforward layers consistently leads to better finetuning performance. Our findings depart from the prevailing assumption that smoothness is desirable, offering a novel perspective on
transformers' functional properties. The code is available at https://github.com/ambroiseodt/vit-plasticity.
Read the full abstract ▾
All authors Ambroise Odonnat, Laetitia Chapel, Romain Tavenard, Ievgen Redko
Machine Learning
Decoupling Variance and Scale-Invariant Updates in Adaptive Gradient Descent for Unified Vector and Matrix Optimization
Zitao Song, Cedar Site Bai, Zhe Zhang et al. (+2 more)
Adaptive methods like Adam have become the $\textit{de facto}$ standard for large-scale vector and Euclidean optimization due to their coordinate-wise adaptation with a second-order nature. More recently,
matrix-based spectral optimizers like
Muon (Jordan et al., 2024b) show the power of treating weight
matrices as
matrices rather than long vectors. Linking these is hard because many natural generalizations are not feasible to implement, and we also cannot simply move the Adam adaptation to the
matrix spectrum. To address this, we reformulate the AdaGrad update and decompose it into a variance adaptation term and a scale-invariant term. This decoupling produces $\textbf{DeVA}$ ($\textbf{De}$coupled $\textbf{V}$ariance $\textbf{A}$daptation), a framework that bridges between vector-based variance adaptation and
matrix spectral optimization, enabling a seamless transition from Adam to adaptive spectral descent. Extensive experiments across
language modeling and image classification demonstrate that DeVA consistently outperforms state-of-the-art methods such as
Muon and SOAP (Vyas et al., 2024), reducing
token usage by around 6.6%. Theoretically, we show that the variance adaptation term effectively improves the blockwise smoothness, facilitating faster convergence. Our implementation is available at https://github.com/Tsedao/Decoupled-Variance-Adaptation
Read the full abstract ▾
All authors Zitao Song, Cedar Site Bai, Zhe Zhang, Brian Bullins, David F. Gleich
Machine Learning · Cross-listed from cs.CL
Uncovering Cross-Objective Interference in Multi-Objective Alignment
Yining Lu and Meng Jiang
We study a persistent failure mode in multi-objective
alignment for large
language models (LLMs), in which scalarized training improves only some objectives while the others degrade. We formalize this phenomenon as cross-objective interference and, to our knowledge, conduct the first systematic study of scalarization
algorithms for multi-objective LLM
alignment. The study shows that interference is pervasive across
algorithms yet strongly model-dependent. To understand how interference arises, we derive a local covariance law stating that an objective improves or degrades at first order according to the sign of the covariance between its reward and the scalarized score. We extend this law to the clipped surrogate objectives of modern reinforcement fine-tuning and show that it still holds under mild conditions. Building on this law, we propose COVariance-floor Enforced Reweighting (COVER), a one-sided controller that raises an objective's weight only when the covariance between its reward and the clipped advantage weight falls below a target. Through extensive experiments, we find that COVER can mitigate cross-objective interference while matching linear scalarization when objectives already co-improve. Finally, to explain why interference is model-dependent, we complement the local covariance law with a global convergence analysis. This analysis gives sufficient conditions for the non-convex scalarized objective to satisfy the Polyak–Łojasiewicz condition and relates interference to model geometry.
Read the full abstract ▾
Machine Learning
T-STAR: A Context-Aware Transformer Framework for Short-Term Probabilistic Demand Forecasting in Dock-Based Shared Micro-Mobility
Jingyi Cheng, Gonçalo Homem de Almeida Correia, Oded Cats et al. (+1 more)
Reliable short-term demand
forecasting is essential for managing shared micro-mobility services and ensuring responsive, user-centered operations. This study introduces T-
STAR (Two-stage Spatial and Temporal Adaptive contextual Representation), a novel
transformer-based probabilistic framework designed to forecast station-level bike-sharing demand at a 15-minute resolution. T-
STAR addresses key challenges in high-resolution
forecasting by disentangling consistent demand patterns from short-term fluctuations through a hierarchical two-stage structure. The first stage captures coarse-grained hourly demand patterns, while the second stage improves prediction accuracy by incorporating high-frequency, localized inputs, including recent fluctuations and real-time demand variations in connected metro services, to account for temporal shifts in short-term demand. Time series
transformer models are employed in both stages to generate probabilistic predictions. Extensive experiments using Washington D.C.'s Capital Bikeshare data demonstrate that T-
STAR outperforms existing methods in both deterministic and probabilistic accuracy. The model exhibits strong spatial and temporal robustness across stations and time periods. A zero-shot
forecasting experiment further highlights T-
STAR's ability to transfer to previously unseen service areas without retraining. These results underscore the framework's potential to deliver granular, reliable, and uncertainty-aware short-term demand forecasts, which enable seamless integration to support
multimodal trip planning for travelers and enhance real-time operations in shared micro-mobility services.
Read the full abstract ▾
All authors Jingyi Cheng, Gonçalo Homem de Almeida Correia, Oded Cats, Shadi Sharif Azadeh
Machine Learning
Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
Xinyu Zhao, Qingyun Sun, Jiayi Luo et al. (+2 more)
Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph
datasets. However, existing zero-shot GAD methods largely ignore intrinsic
geometric differences across diverse anomaly patterns, substantially limiting their cross-domain generalization. In this work, we reveal that anomaly detectability is highly dependent on the underlying
geometric properties and that
embedding graphs from different domains into a single static
curvature space can distort the structural signatures of anomalies. To address the challenge that a single
curvature space cannot capture geometry-dependent graph anomaly patterns, we propose GAD-MoRE, a novel framework for zero-shot Generalizable Graph Anomaly Detection with a Mixture of Riemannian Experts architecture. Specifically, to ensure that each anomaly pattern is modeled in the Riemannian space where it is most detectable, GAD-MoRE employs a set of specialized Riemannian expert networks, each operating in a distinct
curvature space. To construct
topology-aware inputs for the subsequent Riemannian experts, we introduce an anomaly-aware multi-
curvature feature
alignment module that combines dimensionality reduction with
Laplacian feature selection over parallel feature branches. Finally, to facilitate better generalization beyond seen patterns, we design a
memory-based dynamic router that adaptively assigns each input to the most compatible expert based on historical reconstruction performance on similar anomalies. Extensive experiments in the zero-shot setting demonstrate that GAD-MoRE significantly outperforms state-of-the-art generalist GAD baselines.
Read the full abstract ▾
All authors Xinyu Zhao, Qingyun Sun, Jiayi Luo, Xingcheng Fu, Jianxin Li
Machine Learning
Designing a Robust, Bounded, and Smooth Loss Function for Improved Supervised Learning
Soumi Mahato and Lineesh M.C
The loss function is crucial to machine learning, especially in supervised learning frameworks. It is a fundamental component that controls the behavior and general efficacy of learning
algorithms. However, despite their widespread use, traditional loss functions have significant drawbacks when dealing with high-dimensional and outlier-sensitive
datasets, which frequently results in reduced performance and slower convergence during training. In this work, we develop a robust, bounded, and smooth (RoBoS-NN) loss function to resolve the aforementioned hindrances. The generalization ability of the loss function has also been theoretically analyzed to rigorously justify its robustness. Moreover, we implement RoboS-NN loss in the framework of a neural network (NN) to forecast time series and present a new robust
algorithm named $\mathcal{L}_{\text{RoBoS}}$-NN. To assess the potential of $\mathcal{L}_{\text{RoBoS}}$-NN, we conduct experiments on multiple real-world
datasets. In addition, we infuse outliers into data sets to evaluate the performance of $\mathcal{L}_{\text{RoBoS}}$-NN in more challenging scenarios. Numerical results show that $\mathcal{L}_{\text{RoBoS}}$-NN outperforms the other
benchmark models in terms of accuracy measures.
Read the full abstract ▾
Machine Learning
Improved Sampling Schedules for Discrete Diffusion Models
Alberto Foresti, Mustapha Bounoua, Giulio Franzese et al. (+2 more)
Uniform Discrete
Diffusion Models have emerged as a powerful paradigm for generative modeling on sequence data; however, the information-theoretic principles governing their reverse processes remain underexplored. In this work, we bridge this gap by analyzing the reverse process dynamics through the lens of thermodynamic
entropy production and dynamical activity. We use a variational expression of the discrete Wasserstein distance to characterize the dynamics of the generation process. Leveraging these insights, we first introduce the Entropic Discrete Schedule (EDS), which aligns with
entropy production, and later construct the Wasserstein Discrete Schedule (WDS), which combines
entropy production and dynamical activity to act as a
geometric cost. Our experimental results on
language modeling show that WDS provide the same results as uniform while using up to half of the computations on the MBPP
benchmark. The code is available at https://github.com/AlbertoForesti/impscheds.
Read the full abstract ▾
All authors Alberto Foresti, Mustapha Bounoua, Giulio Franzese, Luca Ambrogioni, Pietro Michiardi
Machine Learning · Cross-listed from math.NA
Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter
Yuhan Wu, Jan Willem van Beek, Victorita Dolean et al. (+1 more)
Deep learning-based hybrid iterative methods (DL-HIMs) integrate classical numerical solvers with neural operators, utilizing their complementary spectral biases to accelerate convergence. Despite this promise, many DL-HIMs stagnate at false fixed points where neural updates vanish while the physical residual remains large, raising questions about reliability in scientific computing. In this paper, we provide evidence that performance is highly sensitive to training paradigms and update strategies, even when the neural architecture is fixed. Through a detailed study of a DeepONet-based hybrid iterative numerical transferable solver (HINTS) and an FFT-based
Fourier neural solver (FNS), we show that significant physical residuals can persist when training objectives are not aligned with solver dynamics and problem physics. We further examine Anderson acceleration (AA) and demonstrate that its classical form is ill-suited for nonlinear neural operators. To overcome this, we introduce physics-aware Anderson acceleration (PA-AA), which minimizes the physical residual rather than the fixed-point update. Numerical experiments confirm that PA-AA restores reliable convergence in substantially fewer iterations. These findings provide a concrete answer to ongoing controversies surrounding AI-based PDE solvers: reliability hinges not only on architectures but on physically informed training and iteration design.
Read the full abstract ▾
All authors Yuhan Wu, Jan Willem van Beek, Victorita Dolean, Alexander Heinlein
Machine Learning
Sharpness-Aware Hybrid Model Learning for Architecture-Agnostic Parameter Estimation
Naoya Takeishi
Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, the unknown parameters of the scientific model cannot necessarily be estimated properly, since the flexibility of the machine learning model might make the scientific model part effectively ignored in prediction. We may avoid it by applying some regularization, but the formulation of such regularizers typically depends on model architectures and domain knowledge. In this paper, we propose an architecture-agnostic method to learn hybrid models while properly estimating the scientific parameters. The idea is to use the flatness of loss minima to achieve model simplicity, based upon the Occam's razor principle. We employ the idea of sharpness-aware minimization and adapt it to the hybrid modeling setting. Numerical experiments demonstrate the effectiveness of the SAM-based hybrid model learning for scientific parameter estimation.
Read the full abstract ▾
Machine Learning
AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
Yuming Li, Qingyu Li, Chengyu Bai et al. (+6 more)
Reinforcement learning from human feedback (RLHF) shows promise for aligning
diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and static sampling strategies. These methods treat all
prompts and denoising steps uniformly, ignoring substantial variations in sample learning value as well as the dynamic nature of critical exploration moments. To address this issue, we conduct a detailed analysis of the internal
attention dynamics during GRPO training and uncover a key insight:
attention entropy can serve as a powerful dual-signal proxy. First, across different samples, the relative change in
attention entropy ({\Delta}
Entropy), which reflects the divergence between the current policy and the base policy, acts as a robust indicator of sample learning value. Second, during the denoising process, the peaks of absolute
attention entropy (
Entropy(t)), which quantify
attention dispersion, effectively identify critical timesteps where high-value exploration occurs. Building on this observation, we propose Adaptive
Entropy-Guided Policy Optimization (AEGPO), a novel dual-signal, dual-level adaptive optimization strategy. At the global level, AEGPO uses {\Delta}
Entropy to dynamically allocate rollout budgets, prioritizing
prompts with higher learning value. At the local level, it exploits the peaks of
Entropy(t) to guide exploration selectively at critical high-dispersion timesteps rather than uniformly across all denoising steps. By focusing computation on the most informative samples and the most critical moments, AEGPO enables more efficient and effective policy optimization. Experiments on text-to-image generation tasks demonstrate that AEGPO significantly accelerates convergence and achieves superior
alignment performance compared to standard GRPO variants.
Read the full abstract ▾
All authors Yuming Li, Qingyu Li, Chengyu Bai, Xiangyang Luo, Zeyue Xue, Wenyu Qin, Meng Wang, Yikai Wang, Shanghang Zhang
Machine Learning · Cross-listed from math.OC
RanSOM: Second-Order Momentum with Randomized Scaling for Constrained and Unconstrained Optimization
El Mahdi Chayti and Mohamad Fakhouri
Second-order momentum corrects the lag of momentum behind the current gradient with a Hessian-vector product (HVP), but existing corrections need either a Lipschitz Hessian or extra forward and backward passes at an auxiliary point. We show that randomizing the step length removes this trade-off: if the step is exponentially distributed with mean $\eta$, a Stein-type identity makes $\eta$ times one HVP at the new iterate an estimate of the gradient change that is unbiased in expectation over the step, and this HVP shares its forward pass with the next gradient. The resulting method, RanSOM-E, works with normalized, sign, and
Muon-type steps, and a Beta-distributed variant, RanSOM-B, keeps Frank-Wolfe iterates feasible. For objectives with Lipschitz gradient and heavy-tailed gradient and Hessian noise with tail indices $p, q \in (1,2]$, RanSOM-E attains the optimal oracle-complexity exponents for every pair $(p,q)$, including $p \neq q$, without a Lipschitz Hessian or clipping ($\mathcal{O}(\varepsilon^{-3})$ for $p = q = 2$). On CIFAR-10 with ResNet-20, we detect no accuracy difference from existing second-order momentum methods, and its mean update time is lower than that of the auxiliary-point method.
Read the full abstract ▾
Machine Learning
Calibrating Tabular Anomaly Detection via Optimal Transport
Hangting Ye, He Zhao, Wei Fan et al. (+4 more)
Tabular anomaly detection (TAD) remains challenging due to the heterogeneity of tabular data: features lack natural relationships, vary widely in distribution and scale, and exhibit diverse types. Consequently, each TAD method makes implicit assumptions about anomaly patterns that work well on some
datasets but fail on others, and no method consistently outperforms across diverse scenarios. We present CTAD (Calibrating Tabular Anomaly Detection), a model-agnostic post-processing framework that enhances any existing TAD detector through sample-specific calibration. Our approach characterizes normal data via two complementary distributions, i.e., an empirical distribution from random sampling and a structural distribution from K-means centroids, and measures how adding a test sample disrupts their compatibility using Optimal Transport (OT) distance. Normal samples maintain low disruption while anomalies cause high disruption, providing a calibration signal to amplify detection. We prove that OT distance has a lower bound proportional to the test sample's distance from centroids, and establish that anomalies systematically receive higher calibration scores than normals in expectation, explaining why the method generalizes across
datasets. Extensive experiments on 34 diverse tabular
datasets with 7 representative detectors spanning all major TAD categories (density estimation, classification, reconstruction, and isolation-based methods) demonstrate that CTAD consistently improves performance with statistical significance. Remarkably, CTAD enhances even state-of-the-art deep learning methods and shows robust performance across diverse hyperparameter settings, requiring no additional tuning for practical deployment.
Read the full abstract ▾
All authors Hangting Ye, He Zhao, Wei Fan, Xiaozhuang Song, Dandan Guo, Yi Chang, Hongyuan Zha
Machine Learning · Cross-listed from cs.RO
SuReNav: Superpixel Graph-based Constraint Relaxation for Navigation in Over-constrained Environments
Keonyoung Koh, Moonkyeong Jung, Samuel Seungsup Lee et al. (+1 more)
We address the over-constrained planning problem in semi-static environments. The planning objective is to find a best-effort solution that avoids all hard constraint regions while minimally traversing the least risky areas. Conventional methods often rely on pre-defined area costs, limiting generalizations. Further, the spatial continuity of
navigation spaces makes it difficult to identify regions that are passable without overestimation. To overcome these challenges, we propose SuReNav, a superpixel graph-based constraint relaxation and
navigation method that imitates human-like safe and efficient
navigation. Our framework consists of three components: 1) superpixel graph map generation with regional constraints, 2) regional-constraint relaxation using graph neural network trained on human demonstrations for safe and efficient
navigation, and 3) interleaving relaxation, planning, and execution for complete
navigation. We evaluate our method against state-of-the-art baselines on 2D semantic maps and 3D maps from OpenStreetMap, achieving the highest human-likeness score of complete
navigation while maintaining a balanced trade-off between efficiency and safety. We finally demonstrate its scalability and generalization performance in real-world urban
navigation with a quadruped
robot, Spot. Code and
Videos are available at https://sure-nav.github.io/.
Read the full abstract ▾
All authors Keonyoung Koh, Moonkyeong Jung, Samuel Seungsup Lee, Daehyung Park
Machine Learning · Cross-listed from cs.CV
RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie et al. (+2 more)
Text-to-image
diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined
fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultural, or stylistic) yet still encoded in model representations. We introduce RAIGen, the first framework, to our knowledge, for label-free rare-attribute discovery in
diffusion models, requiring no predefined minority categories. RAIGen leverages Matryoshka Sparse Autoencoders and a novel minority metric combining
neuron activation frequency with semantic distinctiveness to identify interpretable
neurons whose top-activating images reveal underrepresented attributes. Experiments show RAIGen discovers attributes beyond fixed
fairness categories in Stable
Diffusion, scales to larger models such as SDXL, supports systematic
auditing across architectures, and enables targeted amplification of rare attributes during generation. The project page is available at https://vssilpa.github.io/RAIGen_webpage/ .
Read the full abstract ▾
All authors Silpa Vadakkeeveetil Sreelatha, Dan Wang, Serge Belongie, Muhammad Awais, Anjan Dutta
Machine Learning
On the Non-Identifiability of Steering Vectors in Large Language Models
Sohan Venkatesh and Ashish Mahendran Kurapath
Activation steering methods are widely used to control large
language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and uniquely recoverable from input-output behavior. We show that, under white-box single-layer access, steering vectors are fundamentally non-identifiable due to large equivalence classes of behaviorally indistinguishable interventions. Empirically, we find that orthogonal perturbations achieve near-equivalent efficacy with negligible effect sizes across multiple models and traits, with pre-trained semantic classifiers confirming equivalence at the output level. We estimate null-space dimensionality via SVD of activation covariance
matrices and validate that equivalence holds robustly throughout the operationally relevant steering range. Critically, we show that non-identifiability is a robust
geometric property that persists across diverse
prompt distributions. These findings reveal fundamental interpretability limits and highlight the need for structural constraints beyond behavioral testing to enable reliable
alignment interventions.
Read the full abstract ▾
Machine Learning
FlowDA: Accurate, Low-Latency Weather Data Assimilation via Flow Matching
Ran Cheng and Lailai Zhu
Data assimilation (DA) is a fundamental component of modern weather prediction, yet it remains a major computational bottleneck in machine learning (ML)-based
forecasting pipelines due to reliance on traditional variational methods. Recent generative ML-based DA methods offer a promising alternative but typically require many sampling steps and suffer from error accumulation under long-horizon auto-regressive rollouts with cycling assimilation. We propose FlowDA, a low-latency weather-scale generative DA framework based on flow matching. FlowDA conditions on observations through a SetConv-based
embedding and fine-tunes the Aurora foundation model to deliver accurate, efficient, and robust analyses. Experiments across observation rates decreasing from $3.9\%$ to $0.1\%$ demonstrate superior performance of FlowDA over strong baselines with similar tunable-parameter size. FlowDA further shows robustness to observational noise and stable performance in long-horizon auto-regressive cycling DA. Overall, FlowDA points to an efficient and scalable direction for data-driven DA.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup-Stable-Decay
Binghui Li, Zilin Wang, Fengling Chen et al. (+3 more)
We study optimal learning rate (LR) schedules under the functional scaling law (FSL) framework (Li et al., 2025), which decomposes training dynamics into signal learning and noise forgetting. In power-law kernel regression, these two components are governed by a source exponent $s>0$ and a capacity exponent $q>1$, respectively, with smaller $s$ corresponding to harder tasks. For a fixed training horizon $N$, we characterize the schedules that minimize the final-step loss under a stability constraint and reveal a sharp phase transition. In the easy-task regime $s>1-1/q$, the optimal schedule follows power decay from the beginning of training; in the hard-task regime $s<1-1/q$, it becomes warmup-stable-decay (WSD)-like (Hu et al., 2024), staying at the largest admissible LR for most of training before a final decay. In both regimes, the decay exponent is $2q-1$: task difficulty determines when to decay, while model capacity determines how to decay. Beyond the exact optimum, we study fractional schedules, whose shape is defined over relative training progress. We show that precise tuning of the decay shape is often unnecessary: a broad class of profiles attains the optimal convergence rate, while overly slow terminal decay leads to schedule-induced capacity saturation. Finally, for one-pass SGD in kernel regression, FSL-motivated power-decay schedules achieve optimal last-iterate rates. Experiments support the theoretical predictions and the task-dependent transition between early and delayed decay.
Read the full abstract ▾
All authors Binghui Li, Zilin Wang, Fengling Chen, Shiyang Zhao, Ruiheng Zheng, Lei Wu