Overview

Online learning studies how to make predictions and decisions as data arrive, rather than training once on a fixed dataset. Common approaches include Online Mirror Descent and Follow-the-Regularized-Leader for optimization, exponential-weights methods for choosing among experts, and bandit algorithms when feedback is limited. Researchers analyze regret and mistake bounds in adversarial, stochastic, and changing environments, and apply these methods to areas such as forecasting, auctions, and resource allocation. A central challenge is adapting quickly to change while remaining stable and efficient when feedback is delayed, noisy, or costly.

Latest papers

CardsList

145 papers17 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.

  1. Online Switching Control as Learning with Experts

    Nov 13, 2026Masataka Nakamura, Kaito Ito, Hideaki IshiiFeedback ControlAdaptive Control

  2. Capacity-Constrained Delayed Feedback for Online Conformal Risk Control

    Nov 12, 2026Bowen Wang, Osvaldo SimeoneConformal PredictionConformal Risk Control

  3. How Efficient Is Your Agent? Online Predictive Bounds under Budget Constraints

    Nov 8, 2026Roy Maor Lotan, Shai Feldman, Yaniv RomanoAI Agent EvaluationProcess-Based Agent Evaluation

  4. Where Should Learning Live? Regret Analysis for Text, Parameter, and Joint Adaptation

    Nov 6, 2026Jungtaek Kim, Jaden Park, Jongwon Jeong +2Inference-Time Adaptation of Language ModelsOnline Learning

  5. Self-Directed Apple Tasting

    Nov 4, 2026Tanmay Devale, Reed Phillips, Arvind RamaswamiOnline LearningStatistical Learning Theory

  6. Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning

    Nov 4, 2026Hanzhang Qin, Sophie H. Yu, Yuewei Zhang +1LLM RoutingCost-Aware Inference

  7. End-to-End Stability of Online Active Learning in Large-Scale Neural Systems

    Nov 2, 2026Shuiwen Shen, Jinhua Zhang, Chenlei Hou +6Online LearningActive Learning

  8. Streaming Virtual Metrology via Lightweight Adaptation under Temporal Distribution Shifts

    Oct 31, 2026Doyun Choi, Cheonwoo Lee, Younghyun Han +5Distribution Shift RobustnessOnline Learning

  9. Learning to bid and bundle: a posterior-sampling agent for online retail

    Oct 30, 2026Hadi MohammadiAutomated BiddingOnline Learning

  10. Online gas classification at the edge

    Oct 27, 2026Ton Juny Pina, Hugh Greatorex, Elisabetta ChiccaClassificationBinary Neural Networks

  11. Constrained Gradient Equilibrium: Approachability under Locally Constrained Adversaries

    Oct 25, 2026Kaicheng Zhang, Lujing Zhang, Yifei Pang +3Online LearningConstrained Optimization

  12. Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System

    Oct 23, 2026Alban Farchi, Marcin Chrust, Massimo Bonavita +3Weather ForecastingData Assimilation

  13. A Simple and Unified Method for Gradient-Variation Regret

    Oct 19, 2026Hang Yu, Peng ZhaoOnline LearningDynamic Regret Minimization

  14. No-Regret Language Generation

    Oct 16, 2026Jiaxun Li, Vinod Raman, Ambuj TewariText GenerationMinimax Regret

  15. Online Quantile Omniprediction for Proper Losses

    Oct 15, 2026Hyunsuk Kim, Isaac Gibbs, Michael W. Mahoney +1Probabilistic ForecastingQuantile Regression

  16. Longitudinal Learner Participation Profiling in Online Learning: Heterogeneous Consensus Clustering under Unequal Observation Windows

    Oct 12, 2026David Otoo-Arthur, Terence L. van ZylEducational Data MiningClustering

  17. A Time-Synchronous Prequential Evaluation Framework for Next-Week Student Disengagement Prediction from Moodle LMS Logs

    Oct 12, 2026David Otoo-Arthur, Terence L. van ZylEarly Warning DetectionEducational Data Mining

  18. To Defer or Not to Defer? Online Learning with LLMs and Congested Experts

    Oct 10, 2026Vasileios Saketos, William Reveillard, Alexandre Proutiere +2Learning to DeferOnline Learning

  19. Conformal Sequential Decision Making With Cost and Sublinear Policy Regret Guarantees

    Oct 10, 2026Jayadev Naram, Giuseppe Durisi, Matteo Zecchin +1Sequential Decision MakingOnline Learning

  20. Simultaneous Competitive and Regret Guarantees for TCP Acknowledgment

    Oct 9, 2026Tsubasa Harada, Yasushi Kawase, Hanna SumitaOnline Learning with Expert AdviceMinimax Regret

  21. Beyond Second-Order Information: Paid Logistic Regression with Noisy Features

    Oct 9, 2026Sanghwa Kim, Kyoungseok Jang, Se-Young YunOnline LearningLogistic Regression

  22. AdaptLSTM: Efficient Adaptive Online Learning for Cloud Workload Forecasting under Distribution Drift

    Oct 8, 2026Xinhua Miao, Bowei Yang, Zhengong CaiOnline LearningAdaptive Learning

  23. Optimally Pacing Budget Spending and Learning

    Oct 8, 2026Mark Braverman, Jingyi Liu, Jieming Mao +2Online LearningOnline Resource Allocation

  24. Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return Prediction

    Oct 7, 2026Jonathan Chang, Zimeng LyuStock Price ForecastingTime Series Forecasting

  25. sHAIL-Causal: A Sequential Staircase Procedure for Invariant Causal Predictor Discovery

    Oct 5, 2026Ernest FokouéCausal DiscoveryCausal Inference