Online Convex Optimization Against Adversaries with Memory and Application to Statistical Arbitrage

Autor:	Anava, Oren, Hazan, Elad, Mannor, Shie
Rok vydání:	2013
Předmět:	Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	The framework of online learning with memory naturally captures learning problems with temporal constraints, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obtaining optimal regret bounds for both convex and strongly convex losses. The second algorithm attains the optimal regret bounds and applies more broadly to convex losses without requiring Lipschitz continuity, yet is more complicated to implement. We complement our theoretic results with an application to statistical arbitrage in finance: we devise algorithms for constructing mean-reverting portfolios. Comment: 22 pages, 2 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1302.6937 Zobrazit plný text záznamu View this record from Arxiv