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 64
OTROPE: Optimal Transport-based Robust Off-policy Evaluation for Large Language Models
Reliable evaluation of large language models (LLMs) is essential for their development and deployment, yet is often costly, risky, and difficult to perform safely online.Stochastic Optimization Under Power-Law Spectra: Tight Bounds and Shuffling Analysis
Recent work has established that power-law spectral conditions on data enable tight convergence bounds for deterministic gradient descent, resolving the conflict between classical exponential bounds…GNA: Granular Neighbor Assembly for Retrieval-Augmented Multivariate Time-Series Forecasting
Deep forecasters predict from a fixed-length lookback window, and lengthening it gives diminishing returns at a growing cost.MoRE: Scaling mixture of experts with hardware-aware low-rank routing
Mixture-of-Experts (MoE) layers are central to frontier language models, and recent architectures push toward more and smaller experts.Cheap and Powerful Tests for Supervised Subspaces: Per-Component Inference for PLS
Partial Least Squares (PLS) regression extracts a few outcome-aligned directions in a high-dimensional X and is widely used across applied science, but inference on the resulting fit is either…Adapting Linear-Time Architectures for Tabular In-Context Learning
Tabular foundation models achieve strong performance by conditioning on labelled examples in context, but softmax attention limits their use on large datasets.Finite-Sample Theory for Fitted Q-Iteration When Actions Are Functions
Offline reinforcement learning seeks optimal decision rules from previously collected data.LOCO-AdaMP: Built-in LOCO Inference for Adaptive Minipatch Ensembles with Enhanced Prediction
As black-box machine learning models become increasingly common, extracting interpretations with uncertainty quantification has become a critical challenge.Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction
Retrieval-augmented generation (RAG) lets language models answer questions more accurately by consulting relevant documents.Plug-and-Play Methods Provably Converge Even with Improperly Trained Denoisers: Convergence by Architectural Design
Plug-and-Play (PnP) methods replace proximal operators with learned denoisers, which produce state-of-the-art reconstruction quality, but sacrifice the variational interpretation and convergence…Simulation-Free Learning of GP-SDEs from Irregular Observations
Gaussian process stochastic differential equations (GP-SDEs) provide a flexible Bayesian model for unknown continuous-time state dynamics with uncertainty quantification, but learning and inference…Can Tabular Foundation Models Amortize Statistical Inference?
For decades, statistical inference has largely been developed one problem at a time.Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks
As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search.Offline Policy Evaluation via Mixed Bellman Residuals and Adaptive Critic Representations
Evaluating a target policy using data generated by a different behavior policy remains a fundamental challenge in reinforcement learning.Schrödinger--Föllmer Actor--Critic: Diffusion Policy Improvement with Finite-Sample Analysis
Diffusion policies represent multimodal action distributions, but an advantage-weighted update does not specify how to sample from the resulting target distribution.Minimax-Optimality of Posterior Sampling for Reinforcement Learning
Posterior sampling for reinforcement learning (PSRL) is one of the simplest and most effective exploration methods, but a basic question has remained open: does unmodified PSRL achieve minimax…The Statistical Benefits of Multiple Responses for Learning from Demonstrations
Many generative systems return multiple candidate responses and are evaluated according to the best one.Sharp training-conditional coverage for conformal prediction under covariate shift
Weighted split conformal prediction reweights calibration scores by the likelihood ratio between the test and training covariate distributions and guarantees marginal coverage under covariate shift.Domain-Adapted Diffusion Models for Conditional Independence Testing
Conditional independence (CI) is a fundamental concept in statistics and machine learning.SLP-ProbHard: Probabilistic Hard-Constrained Learning via Structural Latent Parameterization
Many probabilistic predictors must satisfy exact structure in every stochastic realization, yet common hard-constraint approaches form predictions in ambient coordinates and then correct or project…