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 65
Neural Scaling Laws of Transformer Operator Network
Transformers have emerged as powerful architectures for learning solution operators of physical systems.Calibrated Derivative-Process Sensitivity for Gaussian-Process Variable Selection
Automatic relevance determination (ARD), the default tool for variable selection in Gaussian-process (GP) regression, ranks inputs by inverse lengthscales -- which measure how fast a function…Sparsity by Default: The Theory and Practice of ARD in Gaussian Process Regression for Variable Selection
Automatic relevance determination (ARD) is the standard device for input selection in Gaussian process (GP) regression.Correct then Forecast: Observer State-Space Models for Time Series Forecasting
Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement.Quantifying Behavioral Tails in Black-Box Language Models
We introduce RareTrap, a framework for estimating the probability of severe behaviors in black box large language models (LLMs).Benign Overfitting for General Norms and Distributions
Understanding why predictors can generalize despite interpolating noisy training data is a central puzzle in machine learning.Reliable Replay through Spatial Coherence in Online Continual Learning
Continually adapting models to new tasks requires retaining earlier knowledge under limited memory and computation.A Statistical Perspective on Knowledge Distillation: Foundations, Classical Methods, and Large Language Model Extensions
Knowledge Distillation (KD) has emerged as a vital paradigm for transferring the capabilities of high-capacity models to efficient ``student'' counterparts, addressing critical challenges in…Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects
Estimating causal effects with continuous treatments in observational studies is challenging due to confounding, model misspecification, and high-dimensional covariates.Multi-Marginal Inverse Optimal Transport for Contrastive Learning Via Explicit Anchor-Positive-Negative Coupling
Inverse Optimal Transport (OT) based methods for representation learning learn representations such that the global OT coupling between a pair of data marginals in the representation space…Oracle-Efficient Online Classification with Stochastic Inputs and Adversarial Outputs
We consider contextual binary prediction with i.i.d. contexts from an unknown distribution and adaptively chosen losses.An Active-Bottleneck Mechanism for Weak-to-Strong Generalization
Weak-to-strong generalization (W2SG) occurs when a student trained on a teacher's predictions outperforms that teacher.Valid and Efficient Split Conformal Regression for Time Series
We study conformalized quantile regression and conformalized median regression that fit a model on one block of a time series and calibrate the conformal interval on the adjacent block.Conformal Coverage of Time Series: Validity and Inference
Conformal prediction provides marginal coverage guarantees, yet practitioners may wonder if the observed coverage is truly abnormal or consistent with sampling variation.Two-Sample Testing for Inhomogeneous Random Graphs in Non-Integral $L_r$ Norms
Testing whether two populations of networks share the same edge probabilities is a basic problem in network inference.HARMONIA: Interpretable Graph Learning through Mixtures of Neural Bases
Existing interpretable graph additive models still face limitations in either computational scalability or modeling flexibility.Posterior Regimes and Latent Deception: Variational Bayesian Inference in Hidden Markov Models for Sequential Fraud Detection in Financial Transactions
We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each…Wasserstein Causal Forests for Distribution-Valued Outcomes
This paper proposes Wasserstein Causal Forests (WCF) for settings in which each unit's outcome is itself a probability distribution.Probability Contracts: Accuracy, Coherence, and Decisions Across LLM Interfaces
A probability used for a decision should refer to the same event across equivalent requests.Conformal Factuality Control for Multi-Hop Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) can ground large language models in external evidence, but retrieved context does not guarantee that generated claims are factually supported.