Probability & Statistics · Mathematics & Statistics
Statistics Theory
The newest papers in Statistics Theory that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
321 papers, from 31 August 2026 to 4 November 2026: 287 arXiv preprints and 34 OpenAlex records.
Get the few papers worth your time in Statistics Theory every morning.
Follow Statistics Theory 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 2
Rare Event Constrained Reinforcement Learning with Large Deviations
We study finite-horizon reinforcement learning with a safety constraint on the probability of reaching a failure set.Optimal spectral shrinkage via Krylov approximation
Spectral shrinkage encompasses a broad family of estimators for high-dimensional linear regression that regularize estimation and prediction by applying spectral filters to the sample covariance…Beyond least-favorable distribution pairs: asymptotically instance-optimal robust hypothesis testing
When testing a composite null $\mathcal{P}$ against a composite alternative $\mathcal{Q}$, it has been known since Huber and Strassen (1973) that if a least favorable distribution (LFD) pair exists…Multiclass Classification with Rare Useful Features: Fundamental Limits and the Optimality of Diversity Pursuit Higher Criticism Thresholding
We consider classification in high-dimensional feature spaces where only a vanishing fraction of features are useful and the number of classes may be large.Near-Quadratic Error-Free Graph Matching above Otter's Threshold via Approximate Local Tree Correlation Testing
This paper presents a near-quadratic-time algorithm that correctly matches almost all nodes of two correlated Erdős-Rényi graphs without any incorrect matches.Non-asymptotic analysis of SGLD with discontinuous stochastic gradients: a new route to portfolio CVaR minimization
Conditional-Value-at-Risk (CVaR) optimization is a fundamental tool in portfolio selection, yet its nonsmooth loss structure poses a challenge for the existing theory of stochastic gradient methods…The Statistical Geometry of Latent Recovery in Hidden Markov Models
Hidden Markov models (HMMs) offer an important capability to interpret fitted latent states and transitions.Estimating Average Treatment Effects with Projected Instrumental Variables
In this paper, we develop a projected instrumental variable framework that relaxes conventional assumptions for causal identification with instrumental variables.Optimal Learning in Fairness-Aware Contextual Bandits
Mitigating unfair disparities in sequential decision-making is a growing concern in machine learning.Robust distortion riskmetrics under symmetry, unimodality, and Wasserstein constraints
We study worst-case distortion riskmetrics over symmetric distributions with prescribed mean and variance in a Wasserstein ball around a reference distribution.Lower Bounds on Inference Complexity for Polyak-Ruppert Averaged Stochastic Gradient Descent
In this paper, we establish sharp lower bounds for Gaussian approximation of Polyak-Ruppert averaged stochastic gradient descent with polynomially decreasing step sizes.Adaptive Optimizers Can Get a Policy Ranking Wrong: Momentum, Dependent Data, and a Two-Run Remedy
Operators choosing among decision rules, such as when a battery charges or where an idle taxi goes, rank them by estimated long-run value.Accelerating posterior sampling in Bayesian inverse problems with diffusion models: an online-offline perspective
Bayesian inverse problems require both informative prior models and computationally feasible posterior inference.Bethe Hessian Recovery through the Kesten-Stigum Regime
We show that outlier eigenvectors of the Bethe Hessian achieve weak recovery in the stochastic block model down to the Kesten-Stigum threshold, for every fixed common expected degree $d>1$.On Statistical-Computational Gaps in Graph Combinatorial Testing Problems
We study high-dimensional graph combinatorial hypothesis testing problems in which a signal is supported on the edge set of an unknown subgraph drawn from a class invariant under vertex relabeling.Instance-dependent sequential limits as an exact information ledger
Instance-dependent limits for bandit regret, sequential tests, best-arm identification and Markov decision processes are proved by one chain.Model Collapse Is Avoidable Even as Real Data Vanishes: A Sharp Criterion for Iterative Gaussian Estimation
Large generative models are commonly trained on data collected from the open web, which may contain data produced by previous generations of the same model.Mutual Information Estimation via Triangular Transport Maps: Finite Sample Guarantees and Sample Allocation
We study finite sample guarantees for transport based mutual information estimation.Non-Asymptotic Confidence Regions for Separable Nonlinear Models
This paper studies robust uncertainty quantification for separable nonlinear least squares (SNLLS) problems.Statistical Analysis of Synthetic Data with Verification: A Linear Regression Framework
Synthetic data are widely used for training modern AI systems.