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 Verification of Language Model Responses Under Cost Constraints

    Oct 2, 2026Erfan Hajihashemi, Yanning ShenOnline Learning with Expert AdviceLLM Reliability

  2. Towards a Cloud Fog Edge System for Smart Building

    Oct 1, 2026Christophe Cérin, Mamadou Sow, Frédéric AndrèsOn-Device TrainingEdge ML

  3. LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models

    Sep 30, 2026Junyi Zou, Avrova DonzMeta-LearningResidual Learning

  4. When Is Coarse Supervision Worth It? Cost-Aware Learning under Unknown Aggregation

    Sep 29, 2026Jianyu Xu, Smriti Jha, Aarti Singh +1Cost-Sensitive LearningStatistical Learning Theory

  5. Improving scalable oversight with co-trained monitors

    Sep 28, 2026Joseph H. Rudoler, Kevin Tan, Benedict Tessler +2Scalable OversightAdversarial Robustness

  6. Evasion Attacks on Cost-Utility-Based Adversarial Training for Online AutoML in IoT Networks

    Sep 25, 2026Chukwunonso Henry Nwokoye, Wajiha Zaheer, Khalil El-Khatib +1Adversarial RobustnessAdversarial Training

  7. Online Learning via Learned Latent Bayesian Tracking

    Sep 25, 2026Guy Gerson, Tomer Raviv, Nir Shlezinger +2Online LearningBayesian Filtering

  8. Downside-Controlled Online Forecast Combination under Delayed and Revised Outcomes

    Sep 24, 2026Minkyoung Kim, Hyunjung Byun, Yohan Lee +1Time Series ForecastingOnline Learning

  9. Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptation

    Sep 23, 2026Oren Wright, Haoming Jing, Qiaoan Shen +3Bayesian Neural NetworksBayesian Filtering

  10. Optimal Randomized Proper Online Learning

    Sep 18, 2026Zachary Chase, Idan MehalelOnline LearningStatistical Learning Theory

  11. Online Adaptive Kernel Mixing for Gaussian Process Decision Making

    Sep 17, 2026Kavin Aravindan, Mani Tej Sriram, Gautam Dasarathy +1Bayesian OptimizationOnline Learning with Expert Advice

  12. Online Gradient Computation for Warping Gaussian Process Transformations

    Sep 15, 2026Emilio Ruiz-Moreno, Konstantinos Slavakis, Baltasar Beferull-LozanoGaussian ProcessesOnline Learning

  13. Online local learning for generative thermodynamic computing

    Sep 14, 2026Huilin Wang, Weibing DengThermodynamic ComputingLocal Learning

  14. A Memristive Synapse for Online STDP Learning and Inference in SNNs

    Sep 14, 2026Elia Mateu-Barriendos, Álvaro Gómez-Pau, Daniel Arumí +2Spiking Neural NetworksSpike-Timing-Dependent Plasticity

  15. Not All Speech Is Intent: Adaptive Self-Correcting Inference Layer for Post-ASR False Wake-Up

    Sep 11, 2026Preeti Saraswat, Divya Neelagiri, Anil YadavAdaptive InferenceOnline Learning

  16. Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

    Sep 8, 2026Xiangnan Zhang, Jingxin Liu, Ranqi Lu +6Neural ProcessesTemporal Credit Assignment

  17. No-Regret Mixing of LRU and LFU with Optimal Switching Cost

    Sep 7, 2026Younes Ben Mazziane, Xinying ZouCache ReplacementRegret Minimization

  18. CAROL: Context-Aware Online Learning for Fuzzer Scheduling

    Sep 6, 2026Zirui Liu, Mengfan Xu, Juan Zhai +2Software EngineeringOnline Learning

  19. Adversarial Online Classification with a Preview

    Aug 30, 2026Roi Livni, Sahil SinglaOnline LearningStatistical Learning Theory

  20. Mind the Student: Behavioral and Contextual Cues for Automated Engagement Prediction in Online Learning

    Aug 25, 2026Alperen Kantarci, Visvanathan Ramesh, Gemma RoigOnline LearningEducational Data Mining

  21. Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents

    Aug 15, 2026Tianxin Wei, Zhan Shi, Minhua Lin +14Continual Learning for LLM AgentsLLM Agent Skill Learning

  22. Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning

    Aug 4, 2026Ghadeer Elmkaiel, Michael MuehlebachAerial RoboticsOnline Learning

  23. Personalizing Large Language Model Agents with Small Policy Models

    Jul 31, 2026Dian Jin, Zhi Zhang, Huichao Li +3LLM PersonalizationLLM Agents

  24. Self-Adaptive Learning and Model Predictive Control for Tracking Unknown Dynamics with No Regret

    Jul 29, 2026Atharva Navsalkar, Hongyu Zhou, Vasileios TzoumasModel Predictive ControlDynamical Systems

  25. Distributed Constraint Optimization via Online Learning and Iterative Pricing with Application to Large-Scale Satellite Scheduling

    Jul 28, 2026Itai Zilberstein, Pranav Rajbhandari, Steve Chien +1Distributed OptimizationPotential Games