Scale-free online learning

DOI10.1016/j.tcs.2017.11.021zbMath1388.68255arXiv1601.01974OpenAlexW2963763894MaRDI QIDQ1704560

Dávid Pál, Francesco Orabona

Publication date: 12 March 2018

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1601.01974

zbMATH Keywords

optimizationonline algorithmsonline learningregret bounds

Mathematics Subject Classification ID

Convex programming (90C25) Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27)

Related Items

Optimistic optimisation of composite objective with exponentiated update, SOLO FTRL algorithm for production management with transfer prices, Nonstationary online convex optimization with multiple predictions, Provably efficient reinforcement learning in decentralized general-sum Markov games, Principal component analysis and optimal portfolio, Unnamed Item

Uses Software

• AdaBoost.MH
• AdaGrad

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• A generalized online mirror descent with applications to classification and regression
• 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
• Adaptive and self-confident on-line learning algorithms
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Large margin classification using the perceptron algorithm
• Efficient algorithms for online decision problems
• Scale-Free Algorithms for Online Linear Optimization
• Online Learning and Online Convex Optimization
• How to use expert advice
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Prediction, Learning, and Games