Citation

BibTex format

@inproceedings{Joulani:2016,
author = {Joulani, P and Gyorgy, A and Szepesvari, C},
publisher = {AAAI},
title = {Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms},
url = {http://hdl.handle.net/10044/1/51726},
year = {2016}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - We present a unified, black-box-style method for developingand analyzing online convex optimization (OCO) algorithmsfor full-information online learning in delayed-feedback environments.Our new, simplified analysis enables us to substantiallyimprove upon previous work and to solve a numberof open problems from the literature. Specifically, we developand analyze asynchronous AdaGrad-style algorithmsfrom the Follow-the-Regularized-Leader (FTRL) and MirrorDescentfamily that, unlike previous works, can handle projectionsand adapt both to the gradients and the delays, withoutrelying on either strong convexity or smoothness of theobjective function, or data sparsity. Our unified frameworkbuilds on a natural reduction from delayed-feedback to standard(non-delayed) online learning. This reduction, togetherwith recent unification results for OCO algorithms, allows usto analyze the regret of generic FTRL and Mirror-Descent algorithmsin the delayed-feedback setting in a unified mannerusing standard proof techniques. In addition, the reduction isexact and can be used to obtain both upper and lower boundson the regret in the delayed-feedback setting.
AU - Joulani,P
AU - Gyorgy,A
AU - Szepesvari,C
PB - AAAI
PY - 2016///
TI - Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms
UR - http://hdl.handle.net/10044/1/51726
ER -