Extracting certainty from uncertainty: regret bounded by variation in costs

DOI10.1007/s10994-010-5175-xzbMath1470.68115MaRDI QIDQ1959595

Elad Hazan, Satyen Kale

Publication date: 7 October 2010

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5175-x

zbMATH Keywords

online learning; prediction with expert advice; regret minimization; individual sequences

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

68W27: Online algorithms; streaming algorithms

Related Items

AN ONLINE PORTFOLIO SELECTION ALGORITHM WITH REGRET LOGARITHMIC IN PRICE VARIATION, Lower bounds on individual sequence regret, Regret bounded by gradual variation for online convex optimization

Uses Software

• AdaBoost.MH

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Exponentiated gradient versus gradient descent for linear predictors
• A game of prediction with expert advice
• The weighted majority algorithm
• A decision-theoretic generalization of on-line learning and an application to boosting
• Improved second-order bounds for prediction with expert advice
• Efficient algorithms for online decision problems
• 10.1162/153244301753683726
• Universal Portfolios
• The Nonstochastic Multiarmed Bandit Problem
• Algorithmic Learning Theory
• Prediction, Learning, and Games