Online Learning
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
145 papers17 papers in the last four weeks, down 37% on the four weeks before. 0.1% of all new papers.
Capacity-Constrained Delayed Feedback for Online Conformal Risk Control
How Efficient Is Your Agent? Online Predictive Bounds under Budget Constraints
PROBE), a method for constructing calibrated upper predictive bounds while adaptively allocating a limited budget across agent tasks to reduce the anticipated coverage deficit. Our method calibrates the bounds online using inverse-probability-weighted feedback together with a correction designed to minimize coverage deficit while remaining unbiased. We prove that PROBE provides a coverage guarantee for any finite time horizon while satisfying the budget constraint. Experiments on software engineering, retrieval-augmented generation, and instruction following show that PROBE attains a coverage rate closer to the target level with tighter predictive bounds than a calibrated baseline.Where Should Learning Live? Regret Analysis for Text, Parameter, and Joint Adaptation
Online Learning with Ordered Experts (via Two-point Feedback)
Self-Directed Apple Tasting
Pathwise-Budgeted LLM Routing: Online Allocation with K-Bit Tail-Cost Learning
End-to-End Stability of Online Active Learning in Large-Scale Neural Systems
Streaming Virtual Metrology via Lightweight Adaptation under Temporal Distribution Shifts
Learning to bid and bundle: a posterior-sampling agent for online retail
Online gas classification at the edge
Constrained Gradient Equilibrium: Approachability under Locally Constrained Adversaries
Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System
A Simple and Unified Method for Gradient-Variation Regret
No-Regret Language Generation
Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control Loop
Online Quantile Omniprediction for Proper Losses
Longitudinal Learner Participation Profiling in Online Learning: Heterogeneous Consensus Clustering under Unequal Observation Windows
A Time-Synchronous Prequential Evaluation Framework for Next-Week Student Disengagement Prediction from Moodle LMS Logs
To Defer or Not to Defer? Online Learning with LLMs and Congested Experts
KL-PBD, a learning algorithm that uses Kullback--Leibler lower confidence bounds on the unknown reliability parameters to guide deferral decisions. For confidence levels and horizon , KL-PBD achieves gap-dependent regret when the accuracy at every confidence level is bounded away from the deferral boundary, and worst-case regret. We establish matching lower bounds, showing that these rates are optimal up to logarithmic factors. Finally, we validate our approach on synthetic instances and real-world question-answering datasets, namely GSM8K, NuminaMath, and MedMCQA, using Qwen LLMs.