online learning
A machine learning approach where the model is updated continuously as new data comes in, allowing for adaptive learning in dynamic environments.
- Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback
- Asymptotic theory of SGD with a general learning-rate
- Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning
- Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
- Explaining the Law of Supply and Demand via Online Learning
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
- Improved Regret and Contextual Linear Extension for Pandora's Box and Prophet Inequality
- Incentivizing Truthful Language Models via Peer Elicitation Games
- Learning to price with resource constraints: from full information to machine-learned prices
- Learning-Augmented Algorithms for $k$-median via Online Learning
- Martingale Posterior Neural Networks for Fast Sequential Decision Making
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets
- OmniDraft: A cross-vocabulary, online adaptive drafter for on-device speculative decoding
- Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time
- Online Learning of Neural Networks
- Optimal Mistake Bounds for Transductive Online Learning
- Optimal Mistake Bounds for Transductive Online Learning
- Prediction with expert advice under additive noise
- Replicable Online Learning
- Self-Improving Embodied Foundation Models
- Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
- Time-uniform and Asymptotic Confidence Sequence of Quantile under Local Differential Privacy
- Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning