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 42
Prediction-Powered Data Fusion for Treatment Effect Estimation
Randomized controlled trials (RCTs) identify treatment effects without confounding but are often small, whereas observational studies (OBS) are large but may be confounded.Closing the Horizon Gap in Policy Optimization for Adversarial MDPs
We consider policy optimization for online episodic tabular Markov decision processes (MDPs) with adversarial losses and bandit feedback.Bilevel optimization for data-driven learning of Koopman embeddings using kernel-based autoencoders
Koopman operator theory provides a linear framework for analyzing nonlinear dynamical systems and has become a major tool for data-driven modeling.Density Ratio Estimation with Stein Displacement Fields
Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto…On the estimation and validity of AI time horizons---a statistical look at the METR plot
METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units.Transformer-Based Masked Diffusion Models Provably Learn Distributions with Latent Structure
Masked diffusion models (MDMs) generate discrete data by iteratively unmasking multiple tokens in parallel using a learned mask predictor.Amortised Inference through One-Step Implicit Sampling
Efficient sampling from Bayesian posterior distributions in high dimensions remains a hard problem, despite advances in theory and algorithms.A Distributional Framework for Behavioral Characterization and Risk Management of Large Language Models
Large language models are stochastic by nature.Kernelized Parameter Sensitivity Atlases for Amortized Conditional Interpretability
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard…Minimax Rates for Estimating Powered Sliced Wasserstein Functionals
We study the two-sample estimation of the powered Sliced Wasserstein functional under projected $r$-th moment assumptions.Bayesian Causal Forests for Zero-Inflated Continuous Outcomes
Estimating (heterogeneous) treatment effects is still challenging when the outcome is semicontinuous (i.e., exhibiting both a discrete point mass at zero and a skewed continuous distribution for…Efficient Best-of-N policy evaluation for inference-time alignment
Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model.The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE Solvers
Neural PDE surrogates are trained on numerical solver outputs that contain both physical evolution and solver-specific discretization errors.The Geometry of Anisotropic Dilation for Optimal Regularization
A central question in data-driven inverse problems is how to construct a regularizer that adapts to the geometry of the data distribution.Benign Overfitting under Heterogeneous Input Fusion
Benign overfitting is extensively studied when learning from a single high-dimensional input, but its behavior under heterogeneous input fusion remains largely unexplored.Global Exponential Convergence of Two-Layer Linear Network Training
We prove global exponential (linear) convergence with an explicit rate in the rich scaling for wide two-layer linear networks trained with smooth Polyak-Lojasiewicz predictor losses.Finite-Rank Logistic Gaussian Processes with Exact Likelihood for Conditional Density Estimation
Conditional density estimation describes how the entire distribution of a response changes with covariates, and in imaging studies also with location.DSReg: Provably Recovering Individual World Latents without Reconstruction
Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through…Adjoint-Based Calibration and Optimal Control of Stochastic Multiscale Bioprocess Digital Twins
We develop a bias-aware digital-twin calibration and control framework for multiscale bioprocess models within a biological systems-of-systems (Bio-SoS) paradigm.Reflected Anchored Langevin Algorithms
First order Langevin algorithms for constrained sampling in machine learning, such as projected Langevin Monte Carlo which are based on discretizations of reflected Langevin dynamics, require…