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 77
Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation
Evaluating an AI system requires disaggregated assessment, as performance varies across domains such as benchmark task types or conversation types in deployed agents.Extreme classification: beating chance with one training example from each class
We study a minimal classification problem: Given independent labeled observations $X\sim P$ and $Z\sim Q$ from two unknown distributions $P,Q$, and given an independent target $Y$ drawn with equal…Complex Problem Solving in Large Language Models: A Statistical Control Survey and Diagnostic Framework
Complex problem solving (CPS) with large language models (LLMs) is often framed as a matter of stronger reasoning or longer generation.Aggregated Posterior Predictive Checks for Generative Modeling
Latent variable generative models are commonly fit using simple priors over latent variables, but draws from these priors often fail to produce realistic data.A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks
We study data-driven early stopping for spectral regularisation methods in the classical non-parametric regression setting.Triply-Scalable Equivariant Gaussian Process Modeling
Gaussian processes (GPs) provide principled probabilistic predictions while encoding prior knowledge, including equivariances.Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers
We propose a decoupled, layerwise method for structurally sparsifying the fully connected layers of pretrained neural networks.On the Identifiability of Mixed Ordinal and Exponential Family Causal DAGs under Linear Parametric Models
The problem of identifiability in linear parametric models (LPMs) whose nodes follow either an ordered logit model or a regular one-parameter exponential family is evaluated.Matching Multi-Loop Complexities with a Single Loop: Optimal Optimization Stationarity and Best-Known Game Stationarity in Nonconvex--Concave Minimax Optimization
We introduce a new single-loop algorithmic framework for smooth nonconvex--concave minimax optimization.Preservation of Log-Concavity and Convergence of Wasserstein-Fisher-Rao Gradient Flows
We study the convergence of Wasserstein-Fisher-Rao (WFR) gradient flows for sampling from probability distributions known up to a normalisation constant.Beyond Quadratic Loss: The Stability Phase Diagram of Adam
Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms.Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
Reliable agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits prompts, memory, retrieval…Gradient Descent with Stochastic Subspaces via Persistence of Memory
Stochastic subspace methods have gained popularity as gradient descent based techniques for large scale optimisation problems, especially in distributed settings.Spatially Adaptive Noise Injection
Diffusion samplers reverse a learned noising process using either stochastic (DDPM) or deterministic (DDIM) updates, which represent endpoints of a single family controlled by a scalar…Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders
Causal discovery aims to recover causal relationships from observed data.How Many Labels Does Model Choice Need? Certificates and Budgets for Selective Prediction
Classifiers can make identical predictions yet require labels to compare their selective performance: confidence ranks weight the same errors differently.Revisiting Distributed Sign-Based Variance Reduction
Sign-based methods reduce communication costs in distributed environments, but aggregating local signs can introduce bias when data are heterogeneous.Rank and computation of the pathlifting Jacobian of a DAG ReLU network
This paper provides a self-contained proof of the rank of the pathlifting Jacobian of a DAG ReLU network by performing an induction on the network's number of hidden nodes.When Edit Flows are Edit Jumps: replicating Edit Flows and EvoFlows
Antibody lead optimization calls for a small, bounded set of edits to an existing candidate: substitutions, but also insertions and deletions.Stable Filters for Generative Modeling of Graph Signals
Generating signals on graphs requires permutation-equivariant models that exhibit stability with respect to relative structural perturbations.