Small-Loss Bounds for Online Learning with Partial Information

DOI10.1287/moor.2021.1204OpenAlexW4220789019MaRDI QIDQ5868953

Karthik Sridharan, Thodoris Lykouris, Éva Tardos

Publication date: 26 September 2022

Published in: Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1711.03639

zbMATH Keywords

online learningpartial informationcontextual banditsregret boundsbandit algorithmshigh probabilityfeedback graphsfirst-order boundssemi-banditssmall-loss bounds

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Logarithmic regret algorithms for online convex optimization
• Asymptotically efficient adaptive allocation rules
• Tracking the best expert
• The weighted majority algorithm
• A decision-theoretic generalization of on-line learning and an application to boosting
• Adaptive and self-confident on-line learning algorithms
• Efficient algorithms for online decision problems
• Intrinsic Robustness of the Price of Anarchy
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• Minimizing Regret With Label Efficient Prediction
• Adaptive routing with end-to-end feedback
• Universal Portfolios
• Learning and Efficiency in Games with Dynamic Population
• Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback
• The Nonstochastic Multiarmed Bandit Problem
• Regret in Online Combinatorial Optimization
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Prediction, Learning, and Games
• Regret Minimization for Reserve Prices in Second-Price Auctions

This page was built for publication: Small-Loss Bounds for Online Learning with Partial Information