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 28
Regret Lower Bound for Online Learning of Quantum States with Logarithmic Loss, with Applications to Quantum State Tomography and Confidence Sequences for Matrix Means
We study the problem of online learning of quantum states with logarithmic loss, which is a quantum generalization of online portfolio selection and has applications to quantum state tomography, the…Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes
Classical PAC-Bayesian generalization theory places prior distributions over Euclidean parameter space $Θ\subseteq \mathbb{R}^D$, causing relative entropy to scale with network dimension $D$.Controlling the False Discovery Rate via Model-Agnostic Importance Measures
Selecting covariates while controlling the false discovery rate (FDR) is critical for interpretable scientific discovery, especially with complex machine learning models.Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax Theory
Test-time scaling can improve the performance of large language models by generating multiple answers to a question and aggregating them.When Is Muon Optimal? Radial Fragility and Minimax Geometry
Muon replaces a matrix gradient by an approximate polar factor and has shown strong empirical performance in neural-network training.Sharp and Stable Label-Free Calibration Certificates from Logical Coherence
Query-conditioned probabilistic predictors answer logically related questions one at a time, and labels to check their calibration are often missing.Market Incentives for AI Safety Investment
Despite their practical significance, modern AI systems pose significant societal risks, including toxicity, malicious use, and misinformation.Conditional Mean Flows: Few-Step Densities for Simulation-Based Inference
Flow matching has emerged as a powerful generative family for simulation-based inference (SBI).Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model
In this paper, we present a lightweight algorithm for modelling tabular data containing both continuous and discrete variables.Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization Algorithm
Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications.Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty Equivalents
Risk-sensitive reinforcement learning (RL) addresses decision-making under uncertainty and adverse outcomes.In-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic Model
Sequence models can generalise in fundamentally distinct ways: extrapolating structures seen in training, or using their prompt to adapt to novel tasks.The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic Regret
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs.SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted Networks
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predictions depend on.Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics Framework
Neural networks often learn low-frequency components before high-frequency ones --- a phenomenon called spectral bias or termed F-principle.Designing Experiments for External Decision Makers
Standard Bayesian experimental design (BED) methods assume the experimenter alone will act on the data, choosing the best action given their own beliefs and goals.Rethinking Successive Rejects Algorithms
In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward.Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop
Neural networks offer critical adaptability for controlling complex systems where nominal modeling proves intractable.Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths
Existing feature attribution methods that account for feature dependencies do not scale to high dimensions.Query-Efficient Rejection Sampling for Parallel Masked Diffusion
Masked diffusion models (MDMs) accelerate generation by unmasking multiple tokens in parallel, but sampling these tokens independently ignores their correlations and biases the output.