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 62
The Statistical Cost of Causal Discovery with Feedback
What determines the unavoidable sample cost of learning cyclic causal structure?GT-PSSM: Unified Probabilistic Framework for Stochastic Dynamics Modeling and Dependency Learning in Multivariate Time Series Anomaly Detection
Multivariate time series anomaly detection (MTAD) is crucial for ensuring the safe and reliable operation of complex systems.AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning
Formulaic alpha discovery is a core challenge in quantitative trading, as identifying alphas that work well together remains difficult.Functional Autoencoders for Amplitude-Phase Representation Learning
Functional data are intrinsically infinite-dimensional, and often exhibit phase variation, where corresponding events occur at different times across observations.CoeF-SFL: Preserving Collaborative Server-Client Learning with Enhanced Communication Efficiency
Split Federated Learning (SFL) enables resource-constrained clients to participate in collaborative training, but vanilla SFL exchanges smashed data and gradients at every batch, which incurs…ABC-Align: Prediction-Powered Alignment with Adaptive Bias Control
Language model post-training is often bottlenecked by the need for human-collected preference data, which is expensive and difficult to scale.Unlocking Few-Step Diffusion for Faithful Previews
Sampling latency compounds in diffusion workflows, where users generate and discard many candidates before keeping one.On the Relation Between Interval Regret and Dynamic Regret
Non-stationary online learning has attracted much attention in recent years, as static regret is insufficient to guide algorithm design in changing environments.Unbiased Top-$k$ Estimation for On-Policy Distillation
On-policy distillation (OPD) is becoming an important component of large language model (LLM) post-training for transferring the reasoning capability of a strong teacher LLM to a weaker student LLM.Understanding Generalization Requires Universal Induction
Classical statistical theory is insufficient to explain the successes of general-purpose AI models, because it depends on handcrafted inductive biases that it cannot justify.Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation
Off-policy evaluation is a foundational component of offline reinforcement learning, aiming to assess and optimize policy performance using pre-collected datasets.Nonnegative DAG Learning via Concomitant Estimation
We study the problem of learning directed acyclic graphs (DAGs) with nonnegative edge weights from observational data.Probabilistic Geodesic Flow Matching on Location-Scale Families
Flow matching (FM) has recently emerged as a promising framework for generative modeling due to its conceptual simplicity and strong empirical performance.Uniform Race: Parameter-Free Approximate Rejection Sampling
We study approximate sampling: given $N$ independent samples from a proposal distribution $μ$, the goal is to select one whose distribution is close to a target $π$ specified only up to a…Two-Timescale Fine-tuning Provably Learns New Features for Two-Layer ReLU Networks
Fine-tuning pre-trained models on specialized tasks with scarce data is central to modern deep learning.Information-Theoretic Analysis of Next-Token Prediction under Markovian Data
We develop an information-theoretic framework for generalization in next-token prediction under temporally dependent data.Statistical Benefits of Fine-Tuning from Pretrained Initialization in Diagonal Linear Networks
Adapting pretrained models to downstream tasks with limited data has become a central paradigm in modern deep learning.Conformal Prediction and Conditional Coverage for Tabular Foundation Models
Tabular foundation models (TFMs) provide predictive distributions for regression, but their prediction regions can exhibit undercoverage or overcoverage even when point predictions are accurate.Fast Learning Rate Transfer in Shallow Linear Networks at Growing Training Horizons
Hyperparameter transfer across model width can substantially reduce the cost of tuning large neural networks, but its behavior when the training horizon grows with width is not fully understood.GUIDE-FBO: Guidance via Uncertainty Intervention and Distributional Exchange for Federated Bayesian Optimization
Federated Bayesian Optimization (FBO) enables distributed agents to collaboratively optimize expensive black-box objectives without sharing raw local observations.