Mind the Duality Gap: Logarithmic regret algorithms for online optimization
نویسندگان
چکیده
We describe a primal-dual framework for the design and analysis of online strongly convex optimization algorithms. Our framework yields the tightest known logarithmic regret bounds for Follow-The-Leader and for the gradient descent algorithm proposed in Hazan et al. [2006]. We then show that one can interpolate between these two extreme cases. In particular, we derive a new algorithm that shares the computational simplicity of gradient descent but achieves lower regret in many practical situations. Finally, we further extend our framework for generalized strongly convex functions.
منابع مشابه
Beyond Logarithmic Bounds in Online Learning
We prove logarithmic regret bounds that depend on the loss LT of the competitor rather than on the number T of time steps. In the general online convex optimization setting, our bounds hold for any smooth and exp-concave loss (such as the square loss or the logistic loss). This bridges the gap between theO(lnT ) regret exhibited by expconcave losses and the O( √ LT ) regret exhibited by smooth ...
متن کاملOn the Generalization Ability of Online Strongly Convex Programming Algorithms
This paper examines the generalization properties of online convex programming algorithms when the loss function is Lipschitz and strongly convex. Our main result is a sharp bound, that holds with high probability, on the excess risk of the output of an online algorithm in terms of the average regret. This allows one to use recent algorithms with logarithmic cumulative regret guarantees to achi...
متن کاملProjection-free Online Learning
The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projections in favor of much more efficient linear optimization steps using the Frank-Wolfe technique. We obtain a range of regret bounds for online convex optimization, with better bounds for specific cases such as stochastic ...
متن کاملEfficient Algorithms for Online Game Playing and Universal Portfolio Management
We introduce a new algorithm and a new analysis technique that is applicable to a variety of online optimization scenarios, including regret minimization for Lipschitz regret functions, universal portfolio management, online convex optimization and online utility maximization. In addition to being more efficient and deterministic, our algorithm applies to a more general setting (e.g. when the p...
متن کاملA new look at shifting regret
We investigate extensions of well-known online learning algorithms such as fixed-share of Herbster and Warmuth (1998) or the methods proposed by Bousquet and Warmuth (2002). These algorithms use weight sharing schemes to perform as well as the best sequence of experts with a limited number of changes. Here we show, with a common, general, and simpler analysis, that weight sharing in fact achiev...
متن کامل