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 36
In-context classification: Calibration and noise in linear attention with softmax readout
We study in-context binary classification in a simple attention model trained to minimise a logistic loss.Can Rényi Accountants Beat Lossless Accountants for DP-SGD?
Recent frameworks in differential privacy (DP), such as privacy loss distributions and $f$-DP, provide lossless representations of the privacy leakage of mechanisms.SCOPE Before You Sample: Conformal Scores Guide Posterior Exploration for Fast and Calibrated Bayesian Predictive Inference
Bayesian predictive regions account for parameter uncertainty but can be poorly calibrated under model misspecification, even with expensive full MCMC.A Generalized McDiarmid Inequality: Sample Reuse and Non-Uniform Unbounded Differences
We develop a novel generalization of McDiarmid's concentration inequality and use it to obtain a uniform law of large numbers result and error bounds on stochastic optimization problems which…Online LLM Personalization from Pairwise Preferences Across Users
Large language models can answer the same question in different styles, but users' preferred styles are hidden and vary across users and questions.Tight End-to-End Accounting for Differentially Private Synthetic Data
Differentially private (DP) pipelines often combine heterogeneous mechanisms, yet their guarantees are best analyzed using different notions of privacy (e.g., bounded range, zCDP, ADP).The Surprising Expressivity of a Single Neuron with Autoregressive Chain-of-Thought
The success of autoregressive language models trained with Chain-of-Thought~(CoT) supervision raises a fundamental question: How simple can a next-token predictor be while still enabling the…Deeply unrolled alternating projections for phase retrieval
Deep unrolling methods for inverse problems augment traditional reconstruction algorithms with learned priors to improve their performance.Near-Optimal Regret Bounds for Monotone Stochastic Optimization under Semi-Bandit Feedback
Stochastic optimization models sequential decision-making under uncertainty, typically assuming known input distributions.Accounting for model error in ensemble variational data assimilation through learned generative dynamics
Many approaches have recently been proposed to combine data assimilation with machine learning for improved forecasts with geophysical models.Monitoring for Shifts at Unknown Times: Parameter-Free Conditional Conformal Martingales
Conditional conformal test martingales provide sequential tests for detecting distribution shifts, using a fixed reference dataset to avoid contamination from test-time samples.On the Statistical Mechanics of Attention
We revisit the statistical mechanics of Transformer attention via modern Hopfield models.Measure Neural Mappings
We introduce and define measure neural mappings (MNMs), which combine measure-dependent neural transport with ensemble consistency for learning operators on probability measures.Learning to Detect Shifts in Unstructured Data Streams via Monitoring-by-Betting
Continuous monitoring of generative AI systems requires detecting distribution shifts in the unstructured data they ingest and generate.Effect of Spherical Parameter Space on Number of Non-Forgetting Tasks and Capacity of Continual Learning
We propose a continuous learning formulation for $T$ non-forgetting tasks with the spherical parameter space $\mathbb{S}^{d-1}(\sqrt{d})$ in asymptotic regime $d\rightarrow \infty$.Imperfect Verifiers, Exact Targets: Inference-Time Scaling for Continuous Generation
Verifier-guided inference-time scaling uses additional computation to score intermediate states and steer generation toward better outputs.What a Data Release Must Preserve for Off-Policy Evaluation
In off-policy evaluation, merging decision-time histories that matter differently for a specified policy value or comparison can make that evaluation unidentified, even with observed actions and…Accuracy and Uncertainty in Machine Deception Detection (Research White Paper)
A deception detector is only as useful as the trust its alarms deserve.Deep Neural Mixed Models for Nonlinear Longitudinal Prediction with Subject-Specific Heterogeneity
Longitudinal health data often exhibit within-subject correlation, subject-specific heterogeneity, and complex nonlinear predictor--response relationships that may not be adequately captured by…Latent-Space Importance Weighting under Covariate Shift
In this work, we propose a transfer learning algorithm for covariate shift, integrating sample reweighting with representation learning.