Logarithmic regret algorithms for online convex optimization

From MaRDI portal
Publication:1009221

DOI10.1007/s10994-007-5016-8zbMath1471.68327OpenAlexW2129160848MaRDI QIDQ1009221

Amit Agarwal, Satyen Kale, Elad Hazan

Publication date: 31 March 2009

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

Full work available at URL: https://doi.org/10.1007/s10994-007-5016-8




Related Items (52)

No Regret Learning in Oligopolies: Cournot vs. BertrandSketch-based empirical natural gradient methods for deep learningOnline active classification via margin-based and feature-based label queriesUnnamed ItemTwo queues with non-stochastic arrivalsPortfolio selection algorithm under financial crisis: a case study with Bursa MalaysiaPredictive online convex optimizationOnline strongly convex optimization with unknown delaysImproving kernel online learning with a snapshot memoryGroup parking permit problemsLogarithmic regret in online linear quadratic control using Riccati updatesDistributed one-pass online AUC maximizationReal-Time Regression Analysis of Streaming Clustered Data With Possible Abnormal Data BatchesDistributed online bandit linear regressions with differential privacyAdaptive moment estimation for universal portfolio selection strategyOnline weakly DR-submodular optimization with stochastic long-term constraintsOnline bandit convex optimisation with stochastic constraints via two-point feedbackUnnamed ItemNo-regret learning for repeated non-cooperative games with lossy banditsOnline variance minimizationPAMR: passive aggressive mean reversion strategy for portfolio selectionOnline renewable smooth quantile regressionOnline distributed dual averaging algorithm for multi-agent bandit optimization over time-varying general directed networksA Simple Method for Predicting Covariance Matrices of Financial ReturnsDynamic regret of adaptive gradient methods for strongly convex problemsAggregating Algorithm for a Space of Analytic FunctionsTechnical Note—Nonstationary Stochastic Optimization Under Lp,q-Variation MeasuresOnline First-Order Framework for Robust Convex OptimizationA generalized online mirror descent with applications to classification and regressionKernel-based online regression with canal lossUnnamed ItemUnnamed ItemUnnamed ItemRegret bounded by gradual variation for online convex optimizationOpinion dynamics with limited informationA modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational boundsScale-invariant unconstrained online learningAdaptive sequential machine learningConcave switching in single-hop and multihop networksOnline Bayesian max-margin subspace learning for multi-view classification and regressionThe recursive variational Gaussian approximation (R-VGA)Competitive Portfolio Selection Using Stochastic PredictionsAn adaptive online learning algorithm for distributed convex optimization with coupled constraints over unbalanced directed graphsConvergence Rate of Incremental Gradient and Incremental Newton MethodsWarranty optimization in a dynamic environmentAN ONLINE PORTFOLIO SELECTION ALGORITHM WITH REGRET LOGARITHMIC IN PRICE VARIATIONUnnamed ItemUnnamed ItemPortfolio selection in non-stationary marketsSuboptimality of constrained least squares and improvements via non-linear predictorsSmall-Loss Bounds for Online Learning with Partial InformationOnline learning over a decentralized network through ADMM



Cites Work


This page was built for publication: Logarithmic regret algorithms for online convex optimization