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 55
On skew-symmetric distributions and their use in Monte Carlo sampling algorithms: coordinate-free, Gibbs-style and manifold versions of the Barker proposal
Skew-symmetric probability distributions provide a principled mechanism for incorporating gradient information into Markov chain Monte Carlo algorithms.Tight Transition Time Bounds for Separable Logistic Regression at the Edge of Stability
We study logistic regression on linearly separable data under gradient descent with a large constant stepsize $η$.Zero Flux: Flow-Based Comparison of High-Dimensional Discrete Distributions
Comparing two high-dimensional discrete distributions has always been a challenging task due to the exponentially growing state space and complex changes in interactions.No Model Required: Text Entropy Rate Filtering Mitigates Iterative Fine-Tuning Collapse
Iterative fine-tuning on synthetic data causes \emph{model collapse}: output diversity narrows as rare patterns are progressively lost, a signature most visible as phrase-level repetition.Langevin-Informed Transfer Learning: Replacing Target Samples by Black-Box Feedback
Many scientific and machine learning systems, from molecular dynamics to diffusion models and beyond, are governed by stochastic dynamics with low-dimensional structure, evolving on slow timescales.Exact Distinguishability in Non-Markovian Decision Processes
Non-Markovian environments are often modeled as Regular Decision Processes (RDPs), where dynamics depend on the interaction history through a finite automaton.The hidden advantage of mask resampling: a theory of masked autoencoders
Why can masked prediction learn useful representations that unmasked reconstruction misses?Lower Bounds for Stochastic First-Order Algorithms with Variance Reduction in Nonconvex--Concave Minimax Optimization
We establish complexity lower bounds for stochastic first-order algorithms in nonconvex--concave minimax optimization, allowing algorithms to use variance reduction.In-context Learning of Single-index Targets: Comparing Kernel and Feature Learners
In-context learning (ICL) enables a pretrained model to infer a task from demonstrations without updating its parameters.Inferring Multi-Timescale Neural Dynamics with Switching Linear Dynamical Systems
Neural activity often exhibits multiple timescales that can vary with behavioral states and task conditions.Generalized Engression Models
We consider estimating the conditional distribution of a multivariate outcome given covariates when its coordinates may be continuous, binary, categorical, ordinal or rankings, and are conditionally…Error-Corrected Inference-Time Scaling for Imperfect Diffusion Models
Inference-time scaling adapts pretrained diffusion models to new sampling tasks without additional training.Pragmatic DML with AI-Learned Representations
Text, images, and other rich covariates are increasingly compressed into AI-learned representations and then used as controls in causal analysis.Sharp Non-Asymptotic Analysis of the Penalized Challenger in $β$-EB-TCI for Bernoulli Bandits
Top-two algorithms are simple and effective for fixed-confidence best-arm identification, but their sharp non-asymptotic behavior is still not well understood.The Curvature of Regret in Contextual Linear Optimization
Decision-focused learning for linear optimization is complicated by the discontinuity of the optimizer, where small cost errors may leave the decision unchanged or move it to a different vertex.Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
There has been a proliferation of sampling algorithms based on Wasserstein gradient flows (WGF) and forward-only diffusion processes (FODP), often accompanied by theoretical guarantees of…Sample complexity bounds for categorical Markov random fields via Discrete Diffusions
Many applications in statistics, economics, and physics require sampling from high-dimensional categorical distributions with local dependence structures.Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
We consider the problem of sampling from Gibbs distributions on matrix spaces whose potential energies are neither convex nor globally gradient-Lipschitz.FERPO: Forward Entropy-Regularized Policy Optimization
Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic.Expected Utility Regret Rule: Minimax and Bayes Optimal Portfolio Choice
This study considers the problem of portfolio choice, where we recommend a portfolio to an investor to maximize the expected utility of their wealth.