Logarithmic Regret Algorithms for Online Convex Optimization

DOI10.1007/11776420_37zbMath1143.90371OpenAlexW1551269584MaRDI QIDQ5307589

Amit Agarwal, Elad Hazan, Satyen Kale, Adam Tauman Kalai

Publication date: 14 September 2007

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

Full work available at URL: https://doi.org/10.1007/11776420_37

Mathematics Subject Classification ID

Related Items (26)

One-pass AUC optimization ⋮ A Low Complexity Algorithm with $O(\sqrt{T})$ Regret and $O(1)$ Constraint Violations for Online Convex Optimization with Long Term Constraints ⋮ Learning in auctions: regret is hard, envy is easy ⋮ Primal-Dual Algorithms for Optimization with Stochastic Dominance ⋮ Opinion dynamics with limited information ⋮ Maxi-Min discriminant analysis via online learning ⋮ Pegasos: primal estimated sub-gradient solver for SVM ⋮ Online Sequential Optimization with Biased Gradients: Theory and Applications to Censored Demand ⋮ Neural network coding of natural images with applications to pure mathematics ⋮ Coordinating Pricing and Inventory Replenishment with Nonparametric Demand Learning ⋮ Online Learning Based on Online DCA and Application to Online Classification ⋮ An Online Policy Gradient Algorithm for Markov Decision Processes with Continuous States and Actions ⋮ Exponentially concave functions and a new information geometry ⋮ Technical Note—Nonparametric Data-Driven Algorithms for Multiproduct Inventory Systems with Censored Demand ⋮ A Linearly Convergent Variant of the Conditional Gradient Algorithm under Strong Convexity, with Applications to Online and Stochastic Optimization ⋮ Online portfolio selection ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Robust exponential memory in Hopfield networks ⋮ Bounds for the tracking error of first-order online optimization methods ⋮ Non-Stationary Stochastic Optimization ⋮ Relative utility bounds for empirically optimal portfolios ⋮ Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent ⋮ Unnamed Item ⋮ On the Effectiveness of Richardson Extrapolation in Data Science

This page was built for publication: Logarithmic Regret Algorithms for Online Convex Optimization