AI & Machine Learning · Computer Science & AI
Machine Learning
The newest papers in Machine Learning that ReadSearch has read, newest first. Each links to its own page, with its authors, date, where it was published and the original.
The newest 5,000 papers, from 12 October 2026 to 5 November 2026: 5,000 arXiv preprints.
Get the few papers worth your time in Machine Learning every morning.
Follow Machine Learning 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 153
On Johnson-Lindenstrauss Transforms for Byzantine-Robust Optimization
The growing scale of data and models in machine learning calls for efficient optimization methods.When Momentum Helps Polyak--Ruppert Averaging
Polyak--Ruppert averaging gives SGD and momentum methods the same asymptotic covariance.Building Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking Evaluation
Telecom language models must combine broad networking knowledge with specialist behavior across routing, broadband services, access technologies, and operational diagnostics while remaining…RANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation Rewards
The integration of Large Language Models and Reinforcement Learning offers a promising direction for complex sequential decision-making tasks, such as multi-hop question answering over knowledge…From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its users.When Does Training on Synthetic Data Provably Work?
High-quality training data are a major bottleneck in machine learning, motivating increasing use of artificially generated data.Poisoning-Based Backdoors Are Not Cryptographic
Defending against a backdoor requires recovering the verifier that decides whether an input is a trigger, since blocking individual triggers fails against an attacker who can generate new ones.On-Policy Transition Distillation
On-policy distillation (OPD) consolidates expert capabilities into a single student by matching teacher and student final-layer distributions on student-generated rollouts.Universal Online Convex Optimization With Delayed Feedback
We study universal online convex optimization with delayed feedback.Auditing Where Concept Bottleneck Accuracy Comes From on CUB
Concept Bottleneck Models (CBMs) promise predictions that humans can inspect and correct through concepts such as "curved beak".Quantifying the Threat: A Bayesian Probabilistic Framework for Heavy Metal Health Risks among Children in the Densu Basin, Ghana
Groundwater in Ghana's Densu River Basin remains a key domestic water source, but multi-metal contamination threatens children's health.MuPACE: Learning to Pace Muon for LoRA Fine-Tuning
Learning rate schedules are typically fixed before training begins, yet when fine-tuning large language models with low-rank adapters (LoRA), the appropriate scale varies substantially with the…PULSE: Personalized Opportunistic Learning for Wearable Devices
Wearable devices increasingly support personalized health and well-being applications, but post-deployment data can differ substantially from those used for training, while purely local adaptation…From Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph Learning
Existing continuous-time graph learning methods rely heavily on complex neural architectures to encode ever-expanding interaction histories.Weak-$L^α$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy Tails
Gradient clipping is a key tool for obtaining high-probability convergence guarantees for stochastic first-order methods under heavy-tailed noise.Causal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation Learning
Causal discovery with latent confounding is particularly challenging, but a common setting in real-world data.Near-Optimal Regret Bounds for UCB-Style Gaussian Process Bandits via Data Thinning
Gaussian process upper confidence bound (GP-UCB) has been widely studied, though its known regret upper bound is suboptimal.Fixed Sets and the Hardness of Computing Correlated Equilibria
We show that computing an approximate correlated equilibrium of a polytope game is PPAD-complete, and thus polynomial-time equivalent to finding a Nash equilibrium.Curriculum Learning for Generative Flexible Docking
Flexible docking is a highly practical task, aiming to predict the joint configuration of a protein-ligand complex from a protein apo structure and a ligand SMILES string.Predicting silent failures of learned inference under restricted access: what measurement physics and prior information explain
Learned priors are used to reconstruct regions that measurements barely reach, and to report uncertainty there.