AI & Machine Learning · Computer Science & AI
Machine Learning (Statistics)
The newest papers in Machine Learning (Statistics) that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
1,749 papers, from 4 September 2026 to 5 November 2026: 1,749 arXiv preprints.
Get the few papers worth your time in Machine Learning (Statistics) every morning.
Follow Machine Learning (Statistics) and ReadSearch reads its new papers each day, then brings you the few worth reading, each with its key finding in a sentence.
Newest papers, page 66
Emergent One-Third Scaling Law as Attention Tries to Concentrate
The neural scaling law relating longer training to better performance through a power law is central to today's large language models (LLMs), yet its origin remains debated.How Reusable Are Benchmarks with Richer Feedback?
We study whether benchmarks reliably guide model selection as developers adapt to evaluation feedback across multiple criteria.REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models
Deep ReLU networks are piecewise-affine mappings that partition the input space into cells, each characterized by a distinct activation pattern.A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets
Linear bandits model sequential decision-making problems with noisy rewards that are linear in the decision variable, where an agent must simultaneously learn about an unknown parameter that governs…FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions
We study fully online fixed-confidence causal discovery without any historical observational data.Uncertainty Quantification of Next Generation Reservoir Computing with Applications to Memory-Driven Dynamical Systems
Nonlinear dynamical systems with memory arise across science and engineering, yet uncertainty quantification for efficient forecasting methods such as Next Generation Reservoir Computing (NGRC)…High-Probability Guarantees for SGD under $β$-Heavy-Tailed Gradient Noise
Stochastic gradient descent (SGD) is widely used to train machine learning models, but subsampling the training data introduces noise into its updates.Overfitting of Spectral Gradient Descent: How Matrix Geometry shapes Generalization and Implicit Bias
We study the generalization of spectral gradient descent (SpecGD) in overparameterized matrix classification with corrupted labels.Recovery-Directed Symbolic Distillation of Neural Likelihoods
Amortized neural likelihoods enable computationally expensive inference for models with analytically intractable or unspecified likelihoods, but their black-box nature limits interpretability.AECSF: Adaptive Ensemble Conditional Score Filtering for High-Dimensional Nonlinear Data Assimilation
Bayesian state estimation for high-dimensional nonlinear dynamical systems entails a fundamental tension between statistical fidelity and computational tractability, as particle weights can…Agnostic Smoothed Online Regression with Adversarial Responses
We study smoothed online prediction with bounded adversarial responses.Learning What to Evaluate: Correlation-Aware Decoupling for Multiobjective Bayesian Optimization
Multiobjective Bayesian optimization (MOBO) with Gaussian process (GP) surrogates is a sample efficient approach to solving multiobjective optimization problems.Affine Geometry of Gaussian ReLU Networks via Conditional Kac-Rice Formulas
We study how the affine geometry of finite ReLU networks is created at random initialization and reorganized by supervised training.Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weak Communication
We study distributionally robust reinforcement learning (DR-RL) in the average-reward setting under weak communication.Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization
Domain Adaptation (DA) often lacks worst-case guarantees, while Distributionally Robust Optimization (DRO) based only on source data centers its ambiguity set at the source law and ignores available…Retrospective Distillation Attribution via Normalized Response Similarity
Model distillation transfers capabilities through supervised fine-tuning (SFT) on teacher responses, often collected from commercial APIs, raising questions of model provenance.Sliced Orlicz-Wasserstein
We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance.Identification of Nonlinear and Dependent Latent Factor Structure through Clique Search
Learning the structure of latent factor models involves two central challenges: (1) estimating the number of latent factors and (2) learning the support of the mapping from latent variables to…Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs
Inferring quantities of interest (QoI) from data is a central task in Science and Engineering.Efficient Message Passing for Partial Differential Equation Priors
Prior information for real-world physical quantities is most elegantly expressed via partial differential equations (PDEs).