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 41
Embedding-Bias in Conditional Independence Testing
To test conditional independence of $X$ and $Y$ given a text or an image $Z$, one conditions on an embedding $ψ(Z)$ in place of $Z$.Minimax Gaussian Mechanisms for Continual Machine Unlearning
Machine unlearning updates a trained model after records are deleted, aiming to match exact retraining without repeating the full training procedure.$σ$Transfer: Uncertainty Transfer from Small to Large Networks under $μ\mathrm{P}$
Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks…Optimal random quantisers for spherically symmetric distributions
Zador's celebrated theorem is a cornerstone of optimal quantisation: it establishes both the weak limit of the empirical distribution of an optimal $n$-point quantiser in $R^d$ and the decay rate of…Softmax Attention on Gaussian Mixtures: Linear When It Can, Selective When It Must
Softmax attention, at the heart of Transformers, has demonstrated remarkable capabilities.Conditional Kernel Stein Discrepancy
Kernel Stein discrepancies (KSDs) provide a versatile tool for comparing distributions.Learning structured linear dynamical systems from missing observations
We consider the problem of learning structured linear dynamical systems over convex sets $\mathcal{K}$, where only a small subset of the observations are available at each time point.RobustLDS: Learning linear dynamical systems under adversarial corruptions
We consider the problem of learning linear dynamical systems under adversarial contamination from a single trajectory of length $T$.Score-Based Learning of Cluster DAGs from Interventions
Graphical approaches to causal abstraction transform a low-level causal directed acyclic graph (DAG) over many measured variables into a smaller, high-level DAG whose nodes cluster the original…Efficient quadratic entropy with distance sketches
We detail scalable methods for approximating the quadratic entropy $p^T d p$ for arbitrary distributions $p$ and common distances $d$ of negative type.Efficient and Generalizable Archetypal Analysis for Discrete Data
Archetypal Analysis (AA) represents observations as convex combinations of extremal data-driven profiles, yielding interpretable low-dimensional descriptions of complex datasets.Diffusion Removes Langevin's Conditioning Dependence: A Sharp Gaussian Analysis
Despite their empirical success, why diffusion models overcome the bottlenecks of classical score-based samplers remains unclear.Exploiting Gradients in Bayesian Inference of Expensive Simulators
Simulators based on differential equations are ubiquitous in science and engineering.Differentiable Systematic Resampling for Variational Sequential Monte Carlo
Particle filters are a standard tool for nonlinear state estimation, but their resampling step is discrete, preventing gradient-based learning in variational sequential Monte Carlo.Credal Machine Learning for Risk-Averse Decision Making
In many machine learning applications, it is necessary to guard against worst-case scenarios and predictions that could result in substantial losses.Quickest Change Detection with Diffusion-Integrated Scores
Classical CUSUM relies on the log-likelihood ratio of the underlying distributions, which cannot generally be computed from finite pre- and post-change samples alone.Verification with Transfer: Exact Information Frontiers and Their Price in Calls
A verifier that accepts or rejects whole answers reveals little: under a flat prior over $k$-bit answers, zero error needs $2^k-1$ verifications.ISBO: Scalable Spatio-Temporal Bayesian Optimization with Log Gaussian Cox Process Models via the INLA-SPDE Approach
Bayesian Optimization (BO) is a popular method for efficiently optimizing expensive black-box objectives.Testing Algebraic Complete Intersections
Given independent and identically distributed samples samples from a probability distribution in a potentially high-dimensional real space, we study the problem of testing whether the distribution…Composite Online-to-Nonconvex Conversion with Optimal Oracle Complexity
We consider stochastic nonsmooth nonconvex composite optimization, which includes several important problems such as constrained optimization and the regularized training of neural networks.