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 27
Equivalence testing and run-count design for stochastic machine-learning experiments
Claims that two training methods perform equally well often rest on a non-significant difference between two or three runs per method.Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients
With infinite-variance gradient noise, SGD can have infinite expected excess objective even when most iterates are close to the optimum.Mesoscopic learning dynamics of extensive-width neural networks
Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central problem in machine learning.Parametric Resonance in Primal-Dual Learning for Slowly Non-Stationary Constrained MDPs
Primal-dual methods for constrained Markov decision processes are analyzed under a two-timescale assumption, with non-stationarity entering through two channels.Task-aware Kernel Stein certificates for Rényi differential privacy
Rènyi differential privacy, based on Rènyi divergence, has become a notion of choice for privacy guarantees.Learning without relearning physical symmetry: an SO(3)-equivariant convolutional network (CNN) on the sphere
Many of the most important datasets in the physical sciences live natively on the sphere, and these data often carry no preferred position or orientation.ENFR: Evidence Networks with Flow-Matched References for Amortized Simulation-Based Model Inference
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and…Graph-Regularized Synthetic Control for Stable Counterfactual Estimation under Donor Redundancy
Synthetic control methods estimate counterfactual outcomes by weighting untreated donor units to match a treated unit before treatment.Margin Certificates for Voting Classifiers under Mixing Dependence
Margin bounds explain why weighted votes generalize after training error vanishes, but dependent observations require concentration arguments that keep the dependence model and failure budget…On Reparameterizing the Score Function
Policy gradients for autoregressive sequence models differentiate each token's log-probability while holding the conditioning history fixed.Certifiably Correct Fréchet Means in Orbit Spaces
We study Fréchet means in orbit spaces of finite orthogonal group actions.Censored Flow Matching for Synthetic Time-to-Event Generation
Generating time-to-event data is increasingly important in survival analysis, but it remains statistically challenging because event times are often censored and thus prevent flexible generative…CoCoNet: Convex Conformal Network for Multi-Dimensional Uncertainty Regions
Conformal prediction (CP) provides distribution-free coverage guarantees under exchangeability, but the efficiency of its prediction regions depends critically on the choice of the conformity score.Constructive Universal Approximation by Infinite-Dimensional Neural Networks via Gaussian-Weighted Ridgelet Transform
Neural networks whose inputs are functions, as in operator learning, are usually shown to be universal by existence arguments, either by reduction to finite-dimensional networks or by…Morpheus-2.0: Multiscale Probabilistic Forecasting with Dual-Axis Attention
A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ.Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy
We propose a general framework for non-interactive locally differentially private (LDP) learning of structured univariate distributions that can be approximated by piece-wise polynomials.Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete Diffusion
Discrete diffusion models have become a powerful framework for modeling complex discrete distributions across a range of applications.StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend Prediction
Score-based diffusion methods usually perturb data with Brownian Gaussian noise, corresponding to a light-tailed forward stochastic differential equation (SDE).A One-Sided McDiarmid-Type Inequality for Heavy Tails via Reverse KL Tensorization
We revisit McDiarmid's inequality, a central tool in statistical learning theory and algorithm analysis.CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHF
Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM judges.