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 51
Does Muon Need Fine-Grained Spectral Shaping?
Muon combines current and past gradients into matrix momentum.Two-Sample Testing for Random Graphs without Vertex Correspondence
Two populations of graphs often have to be compared without any correspondence between their vertices, for instance when networks come from different communities, or when a graph generative model is…When Is a Graph a Covariance? Bayesian Residual Propagation under Covariance Uncertainty
Observing a prediction error at one node can help correct predictions elsewhere, but the benefit depends on the residual dependence between nodes.Beyond Overparameterization: Provable Learning of Input-Convex Multi-Layer Polynomial Networks with Active Queries
The theoretical understanding of multi-layer neural networks is largely confined to overparameterized settings, which obscure parameter identifiability and incur high sample complexity.A Statistical Inference Framework for PMI Estimation and SGNS Word Embeddings
Pointwise Mutual Information (PMI) is a core measure of testing word association, and Skip-gram with Negative Sampling (SGNS) is essentially a method that implicitly factorizes a shifted PMI matrix.Selecting Repetition Counts Across Model Scales in Data-Constrained Pretraining
The repetition count that works best for a small language model may not remain best at a larger scale.Measuring Learned Monotone Temporal Aggregation at Matched Admissibility
Risk regulation imposes directional constraints on scores; we adopt their strict per-input form -- the score monotone non-decreasing in every exposure input -- as a normative commitment.Quantitative Universality of Approximate Message Passing for Rank-One Quadratic Sensing
Approximate Message Passing (AMP) algorithms are attractive as they are computationally efficient and simultaneously admit a precise characterization in terms of the low-dimensional…Diffusion Transformers are Provably Optimal In-context Generators
Generative foundation models are attracting interest for their ability to produce desired outputs from demonstrations given at inference time, without updating parameters.Poisson Autoregression on a Large Network with a Stochastic Block Model Structure
We consider multivariate Poisson autoregressive processes evolving on random networks generated by a Stochastic Block Model.Taylor Representations for Model-Free RL in Networked MDPs
In Networked Markov Decision Processes, transition dynamics are often unknown and the state--action space grows rapidly with the number of agents.G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm
Small language model (SLM) agents need safety controls that track consequences across tool calls with little monitoring overhead.Moment-Accurate Gaussian Mixtures for Constant-Step Stochastic Approximation
Local Gaussian models of constant-step learning predict output variability and expected losses, but weak convergence alone does not justify these moment predictions.Gaussian Limits for SGD Without Stationary Moments
Temporal dependence can separate the Gaussian approximation of stochastic gradient descent from its stationary moments.The Premise Is the Problem: Exchangeability Failure in Self-Monitored Test-Time Adaptation
Modern forecasting models are often updated after deployment so they can respond to changing data.Mitigating Over-squashing without Rewiring: A Sheaf Effective Resistance Perspective
Graph Neural Networks (GNNs) often struggle to capture long-range dependencies due to over-squashing -- a phenomenon in which the repeated compression of node embeddings into finite-size messages…How RL Reshapes LLM Reasoning: Transferability, Coverage, and Scaling Laws
Recent studies on reinforcement learning (RL) report seemingly conflicting evidence about large language model (LLM) reasoning.Risk-Calibrated Proposal Transport for Finite-Particle Diffusion Steering
Inference-time steering combines pretrained diffusion experts or rewards without retraining by changing the dynamics that transport noise to data.Neyman-Pearson Classification with Indecisions: Simultaneous Control of Selective Type I and Type II Errors
Binary classification often requires controlling both type I and type II error rates at prespecified levels.Local Fisher Information Enables Sparse Causal Discovery
Sparse causal discovery calls for methods that exploit graph structure without estimating high-dimensional densities.