Online Learning of Assignments that Maximize Submodular Functions

Which ads should we display in sponsored search in order to maximize our revenue? How should we dynamically rank information sources to maximize value of information? These applications exhibit strong diminishing returns: Selection of redundant ads and information sources decreases their marginal utility. We show that these and other problems can be formalized as repeatedly selecting an assignment of items to positions to maximize a sequence of monotone submodular functions that arrive one by one. We present an efficient algorithm for this general problem and analyze it in the no-regret model. Our algorithm possesses strong theoretical guarantees, such as a performance ratio that converges to the optimal constant of 1-1/e. We empirically evaluate our algorithm on two real-world online optimization problems on the web: ad allocation with submodular utilities, and dynamically ranking blogs to detect information cascades.

[1]  Jan Vondrák,et al.  Maximizing a Submodular Set Function Subject to a Matroid Constraint (Extended Abstract) , 2007, IPCO.

[2]  Matthew J. Streeter,et al.  An Online Algorithm for Maximizing Submodular Functions , 2008, NIPS.

[3]  Yishay Mansour,et al.  From External to Internal Regret , 2005, J. Mach. Learn. Res..

[4]  Jan Vondrák,et al.  Submodularity in Combinatorial Optimization , 2007 .

[5]  Peter Auer,et al.  The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[6]  Vahab S. Mirrokni,et al.  Tight information-theoretic lower bounds for welfare maximization in combinatorial auctions , 2008, EC '08.

[7]  R. Vohra,et al.  Algorithmic Game Theory: Sponsored Search Auctions , 2007 .

[8]  Jan Vondrák,et al.  Maximizing a Monotone Submodular Function Subject to a Matroid Constraint , 2011, SIAM J. Comput..

[9]  Jan Vondrák,et al.  Optimal approximation for the submodular welfare problem in the value oracle model , 2008, STOC.

[10]  Andreas Krause,et al.  Cost-effective outbreak detection in networks , 2007, KDD '07.

[11]  Filip Radlinski,et al.  Learning diverse rankings with multi-armed bandits , 2008, ICML '08.

[12]  Jon Feldman,et al.  Sponsored Search Auctions with Markovian Users , 2008, WINE.

[13]  Adam Tauman Kalai,et al.  Playing Games with Approximation Algorithms , 2009, SIAM J. Comput..

[14]  Jon Feldman,et al.  Algorithmic Methods for Sponsored Search Advertising , 2008, ArXiv.

[15]  Andreas Krause,et al.  Near-optimal Observation Selection using Submodular Functions , 2007, AAAI.

[16]  M. L. Fisher,et al.  An analysis of approximations for maximizing submodular set functions—I , 1978, Math. Program..