Publication:4637004

zbMath1435.68277arXiv1403.3465MaRDI QIDQ4637004

H. Brendan McMahan

Publication date: 17 April 2018

Full work available at URL: https://arxiv.org/abs/1403.3465

zbMATH Keywords

online learning; adaptive algorithms; dual averaging; mirror descent; online convex optimization; regret analysis; follow-the-regularized-leader

Mathematics Subject Classification ID

90C25: Convex programming

68T05: Learning and adaptive systems in artificial intelligence

68-02: Research exposition (monographs, survey articles) pertaining to computer science

68W27: Online algorithms; streaming algorithms

Related Items

Technical Note—Nonstationary Stochastic Optimization Under L_p,q-Variation Measures, Accelerated dual-averaging primal–dual method for composite convex minimization, Unifying mirror descent and dual averaging, Comprehensive study of variational Bayes classification for dense deep neural networks, Relaxing the i.i.d. assumption: adaptively minimax optimal regret via root-entropic regularization, Principal component analysis and optimal portfolio, Sequential testing for elicitable functionals via supermartingales, Make \(\ell_1\) regularization effective in training sparse CNN, Kernel-based online regression with canal loss, A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds

Uses Software

• AdaBoost.MH
• AdaGrad

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• On the delay-differential equations x'(t) + a(t)f(x(t - r(t))) = 0 and x(t) + a(t)f(x(t - r(t)))=0
• A decision-theoretic generalization of on-line learning and an application to boosting
• Introductory lectures on convex optimization. A basic course.
• Adaptive and self-confident on-line learning algorithms
• Mirror descent and nonlinear projected subgradient methods for convex optimization.
• Online Learning and Online Convex Optimization
• On the Generalization Ability of On-Line Learning Algorithms
• 10.1162/153244302760200704
• Online Learning Meets Optimization in the Dual
• Prediction by Categorical Features: Generalization Properties and Application to Feature Ranking
• Prediction, Learning, and Games
• Convex Analysis
• STABILITY RESULTS IN LEARNING THEORY