🤖 Category

cs.LG

2316 papers

Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective

This paper establishes that generative drifting is theoretically equivalent to score matching under Gaussian kernels, providing a spectral and variational framework that explains the empirical superiority of Laplacian kernels, proposes an exponential bandwidth annealing schedule to accelerate convergence, and proves the necessity of the stop-gradient operator through its connection to Wasserstein gradient flows.

Erkan Turan, Maks Ovsjanikov2026-03-11🤖 cs.LG

SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG

The paper introduces SignalMC-MED, a comprehensive benchmark utilizing 22,256 synchronized single-lead ECG and PPG visits to evaluate biosignal foundation models across 20 clinical tasks, demonstrating that domain-specific models with multimodal fusion and full-duration signals outperform general time-series approaches while revealing that larger model sizes do not guarantee superior performance.

Fredrik K. Gustafsson, Xiao Gu, Mattia Carletti, Patitapaban Palo, David W. Eyre, David A. Clifton2026-03-11🤖 cs.LG

When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic

This paper introduces the Overfitting-Underfitting Indicator (OUI) as an efficient, early-stage metric based on hidden neuron activation patterns to distinguish optimal learning rates in PPO actor-critic training, demonstrating its superior ability to prune unpromising runs compared to traditional criteria by revealing distinct structural signatures in actor and critic networks.

Alberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre, Manuel F. Dolz, Jose Duato, Enrique S. Quintana-Ortí2026-03-11🤖 cs.AI

On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer

This paper introduces a family of mean-normalized matrix operator norms to derive width-independent smoothness bounds for deep neural networks, leading to the development of MOGA, a row/column-normalized optimizer that enables stable hyperparameter transfer across model widths and outperforms Muon in speed while maintaining competitive performance.

Ruihan Xu, Jiajin Li, Yiping Lu2026-03-11🤖 cs.LG

From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding

The paper proposes C2FMAE, a coarse-to-fine masked autoencoder that resolves the tension between global semantics and local details in self-supervised learning by employing a cascaded decoder and progressive masking curriculum on a newly constructed multi-granular dataset to achieve hierarchical visual understanding and superior performance across various vision tasks.

Wenzhao Xiang, Yue Wu, Hongyang Yu, Feng Gao, Fan Yang, Xilin Chen2026-03-11🤖 cs.LG

From Data Statistics to Feature Geometry: How Correlations Shape Superposition

This paper challenges the standard view of superposition in neural networks by demonstrating that, unlike in idealized uncorrelated settings where interference is merely noise, realistic feature correlations allow models to arrange features so that interference becomes constructive, thereby naturally forming the semantic clusters and cyclical structures observed in real language models.

Lucas Prieto, Edward Stevinson, Melih Barsbey, Tolga Birdal, Pedro A. M. Mediano2026-03-11🤖 cs.AI

Task Aware Modulation Using Representation Learning for Upsaling of Terrestrial Carbon Fluxes

The paper introduces Task-Aware Modulation with Representation Learning (TAM-RL), a novel framework that combines spatio-temporal representation learning with physically grounded constraints to significantly improve the accuracy and generalizability of global terrestrial carbon flux estimates compared to existing state-of-the-art methods.

Aleksei Rozanov, Arvind Renganathan, Vipin Kumar2026-03-11🤖 cs.LG

Accounting for shared covariates in semi-parametric Bayesian additive regression trees

This paper proposes a novel extension to semi-parametric Bayesian additive regression trees (BART) that resolves non-identifiability and bias issues by modifying tree-generation moves to allow shared covariates between linear and non-parametric components, thereby enabling the modeling of complex interactions while maintaining competitive performance across simulation and real-world applications.

Estevão B. Prado, Andrew C. Parnell, Keefe Murphy + 3 more2026-03-10🤖 cs.LG

A White-Box SVM Framework and its Swarm-Based Optimization for Supervision of Toothed Milling Cutter through Characterization of Spindle Vibrations

This paper presents a white-box support vector machine framework optimized by five meta-heuristic swarm algorithms to monitor the health of toothed milling cutters in real-time by characterizing spindle vibrations and selecting relevant statistical features through Recursive Feature Elimination with Cross-Validation.

Tejas Y. Deo, B. B. Deshmukh, Keshav H. Jatakar, Kamlesh M. Chhajed, S. S. Pardeshi, R. Jegadeeshwaran, Apoorva N. Khairnar, Hrushikesh S. Khade, A. D. Patange2026-03-10🤖 cs.LG

Automated Reinforcement Learning: An Overview

This paper provides a comprehensive overview of Automated Reinforcement Learning (AutoRL), surveying existing literature including recent LLM-based techniques, discussing promising non-tailored methods for future integration, and outlining current challenges and research directions in automating MDP modeling, algorithm selection, and hyper-parameter optimization.

Reza Refaei Afshar, Joaquin Vanschoren, Uzay Kaymak, Rui Zhang, Yaoxin Wu, Wen Song, Yingqian Zhang2026-03-10🤖 cs.LG

Explainable classification of astronomical uncertain time series

This paper proposes an uncertainty-aware, explainable-by-design subsequence-based model that achieves state-of-the-art classification performance for astronomical uncertain time series by incorporating data uncertainty as an input, thereby enabling domain experts to inspect predictions and potentially inspire new theoretical astrophysics developments.

Michael Franklin Mbouopda (LIMOS, UCA), Emille E. O. Ishida (LIMOS, UCA), Engelbert Mephu Nguifo (LIMOS, UCA), Emmanuel Gangler (LPC, UCA)2026-03-10🔭 astro-ph

Survey of Computerized Adaptive Testing: A Machine Learning Perspective

This paper presents a machine learning-focused survey of Computerized Adaptive Testing (CAT), exploring how ML techniques can optimize measurement models, question selection, bank construction, and test control to create more robust, fair, and efficient adaptive assessment systems across various domains.

Yan Zhuang, Qi Liu, Haoyang Bi, Zhenya Huang, Weizhe Huang, Jiatong Li, Junhao Yu, Zirui Liu, Zirui Hu, Yuting Hong, Zachary A. Pardos, Haiping Ma, Mengxiao Zhu, Shijin Wang, Enhong Chen2026-03-10🤖 cs.LG