Efficient Online Linear Optimization with Approximation Algorithms

We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting is in particular interesting since it captures natural online extensions of well-studied \textit{offline} linear optimization problems which are NP-hard, yet admit efficient approximation algorithms. The goal here is to minimize the $\alpha$\textit{-regret} which is the natural extension of the standard \textit{regret} in \textit{online learning} to this setting. We present new algorithms with significantly improved oracle complexity for both the full information and bandit variants of the problem. Mainly, for both variants, we present $\alpha$-regret bounds of $O(T^{-1/3})$, were $T$ is the number of prediction rounds, using only $O(\log{T})$ calls to the approximation oracle per iteration, on average. These are the first results to obtain both average oracle complexity of $O(\log{T})$ (or even poly-logarithmic in $T$) and $\alpha$-regret bound $O(T^{-c})$ for a constant $c>0$, for both variants.

[1]  Nicos Christofides Worst-Case Analysis of a New Heuristic for the Travelling Salesman Problem , 1976, Operations Research Forum.

[2]  Santosh S. Vempala,et al.  Efficient algorithms for online decision problems , 2005, J. Comput. Syst. Sci..

[3]  Elad Hazan,et al.  Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization , 2008, COLT.

[4]  Adam Tauman Kalai,et al.  Playing games with approximation algorithms , 2007, STOC '07.

[5]  Maria-Florina Balcan,et al.  Approximation algorithms and online mechanisms for item pricing , 2006, EC '06.

[6]  Baruch Awerbuch,et al.  Adaptive routing with end-to-end feedback: distributed learning and geometric approaches , 2004, STOC '04.

[7]  Vasek Chvátal,et al.  A Greedy Heuristic for the Set-Covering Problem , 1979, Math. Oper. Res..

[8]  Reuven Bar-Yehuda,et al.  A Linear-Time Approximation Algorithm for the Weighted Vertex Cover Problem , 1981, J. Algorithms.

[9]  Elad Hazan,et al.  Volumetric Spanners: An Efficient Exploration Basis for Learning , 2013, J. Mach. Learn. Res..

[10]  Sébastien Bubeck,et al.  Convex Optimization: Algorithms and Complexity , 2014, Found. Trends Mach. Learn..

[11]  S. Matthew Weinberg,et al.  Algorithms for strategic agents , 2014 .

[12]  Martin Zinkevich,et al.  Online Convex Programming and Generalized Infinitesimal Gradient Ascent , 2003, ICML.

[13]  David P. Williamson,et al.  Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming , 1995, JACM.

[14]  Takahiro Fujita,et al.  Combinatorial Online Prediction via Metarounding , 2013, ALT.

[15]  Haipeng Luo,et al.  Variance-Reduced and Projection-Free Stochastic Optimization , 2016, ICML.

[16]  Martin Grötschel,et al.  The ellipsoid method and its consequences in combinatorial optimization , 1981, Comb..