Optimization for Approximate Submodularity

We consider the problem of maximizing a submodular function when given access to its approximate version. Submodular functions are heavily studied in a wide variety of disciplines, since they are used to model many real world phenomena, and are amenable to optimization. However, there are many cases in which the phenomena we observe is only approximately submodular and the approximation guarantees cease to hold. We describe a technique which we call the sampled mean approximation that yields strong guarantees for maximization of submodular functions from approximate surrogates under cardinality and intersection of matroid constraints. In particular, we show tight guarantees for maximization under a cardinality constraint and 1/(1+P) approximation under intersection of P matroids.

[1]  Stefanie Jegelka,et al.  Minimizing approximately submodular functions , 2019, ArXiv.

[2]  Amin Karbasi,et al.  Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity , 2018, ICML.

[3]  Amin Karbasi,et al.  Conditional Gradient Method for Stochastic Submodular Maximization: Closing the Gap , 2017, AISTATS.

[4]  Amin Karbasi,et al.  Gradient Methods for Submodular Maximization , 2017, NIPS.

[5]  Avinatan Hassidim,et al.  Submodular Optimization under Noise , 2016, COLT.

[6]  Yang Yu,et al.  Subset Selection under Noise , 2017, NIPS.

[7]  Wei Chen,et al.  Influence Maximization with ε-Almost Submodular Threshold Functions , 2017, NIPS.

[8]  Jan Vondrák,et al.  On Multiplicative Weight Updates for Concave and Submodular Function Maximization , 2015, ITCS.

[9]  Christopher P. Chambers.  Revealed Preference Theory Econometric Society Monographs Revealed Preference Theory , 2015 .

[10]  Andreas Krause,et al.  From MAP to Marginals: Variational Inference in Bayesian Submodular Models , 2014, NIPS.

[11]  Andreas Krause,et al.  Streaming submodular maximization: massive data summarization on the fly , 2014, KDD.

[12]  Nicole Immorlica,et al.  A Unifying Hierarchy of Valuations with Complements and Substitutes , 2014, AAAI.

[13]  Joseph Naor,et al.  Submodular Maximization with Cardinality Constraints , 2014, SODA.

[14]  Éva Tardos,et al.  Equilibrium in Combinatorial Public Projects , 2013, WINE.

[15]  Benjamin Moseley,et al.  Fast greedy algorithms in mapreduce and streaming , 2013, SPAA.

[16]  Joseph Naor,et al.  A Tight Linear Time (1/2)-Approximation for Unconstrained Submodular Maximization , 2012, 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science.

[17]  Shahar Dobzinski,et al.  The computational complexity of truthfulness in combinatorial auctions , 2012, EC '12.

[18]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.

[19]  Jeff A. Bilmes,et al.  Approximation Bounds for Inference using Cooperative Cuts , 2011, ICML.

[20]  Jeff A. Bilmes,et al.  Submodularity beyond submodular energies: Coupling edges in graph cuts , 2011, CVPR 2011.

[21]  Hui Lin,et al.  A Class of Submodular Functions for Document Summarization , 2011, ACL.

[22]  Chandra Chekuri,et al.  Submodular function maximization via the multilinear relaxation and contention resolution schemes , 2011, STOC '11.

[23]  Chandra Chekuri,et al.  Approximation Algorithms for Submodular Multiway Partition , 2011, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[24]  Tim Roughgarden,et al.  From convex optimization to randomized mechanisms: toward optimal combinatorial auctions , 2011, STOC '11.

[25]  Shahar Dobzinski,et al.  Optimal auctions with correlated bidders are easy , 2010, STOC.

[26]  Christos H. Papadimitriou,et al.  On optimal single-item auctions , 2010, STOC '11.

[27]  Maria-Florina Balcan,et al.  Learning submodular functions , 2010, STOC '11.

[28]  Andreas Krause,et al.  Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization , 2010, J. Artif. Intell. Res..

[29]  Hui Lin,et al.  Optimal Selection of Limited Vocabulary Speech Corpora , 2011, INTERSPEECH.

[30]  Andreas Krause,et al.  Budgeted Nonparametric Learning from Data Streams , 2010, ICML.

[31]  David Buchfuhrer,et al.  Computation and incentives in combinatorial public projects , 2010, EC '10.

[32]  Andreas Krause,et al.  Online distributed sensor selection , 2010, IPSN '10.

[33]  Elchanan Mossel,et al.  Inapproximability for VCG-based combinatorial auctions , 2010, SODA '10.

[34]  Andreas Krause,et al.  Online Learning of Assignments , 2009, NIPS.

[35]  Vahab S. Mirrokni,et al.  Non-monotone submodular maximization under matroid and knapsack constraints , 2009, STOC '09.

[36]  Vitaly Feldman,et al.  On the Power of Membership Queries in Agnostic Learning , 2009, COLT.

[37]  Yaron Singer,et al.  Inapproximability of Combinatorial Public Projects , 2008, WINE.

[38]  Christos H. Papadimitriou,et al.  On the Hardness of Being Truthful , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

[39]  Noam Nisan,et al.  Multi-unit Auctions with Budget Limits , 2008, 2008 49th Annual IEEE Symposium on Foundations of Computer Science.

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

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

[42]  Vahab S. Mirrokni,et al.  Maximizing Non-Monotone Submodular Functions , 2011, 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07).

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

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

[45]  Andreas Krause,et al.  Nonmyopic active learning of Gaussian processes: an exploration-exploitation approach , 2007, ICML '07.

[46]  Aranyak Mehta,et al.  Inapproximability Results for Combinatorial Auctions with Submodular Utility Functions , 2005, Algorithmica.

[47]  Uriel Feige,et al.  Approximation algorithms for allocation problems: Improving the factor of 1 - 1/e , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[48]  Shahar Dobzinski,et al.  An improved approximation algorithm for combinatorial auctions with submodular bidders , 2006, SODA '06.

[49]  Noam Nisan,et al.  Approximation algorithms for combinatorial auctions with complement-free bidders , 2005, STOC '05.

[50]  Maxim Sviridenko,et al.  Pipage Rounding: A New Method of Constructing Algorithms with Proven Performance Guarantee , 2004, J. Comb. Optim..

[51]  Jon Kleinberg,et al.  Maximizing the spread of influence through a social network , 2003, KDD '03.

[52]  Vitaly Feldman,et al.  On Using Extended Statistical Queries to Avoid Membership Queries , 2001, J. Mach. Learn. Res..

[53]  U. Feige.  A threshold of ln n for approximating set cover , 1998, JACM.

[54]  Eli Shamir,et al.  Learning by extended statistical queries and its relation to PAC learning , 1995, EuroCOLT.

[55]  Jeffrey C. Jackson,et al.  An efficient membership-query algorithm for learning DNF with respect to the uniform distribution , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[56]  Robert E. Schapire,et al.  Exact identification of circuits using fixed points of amplification functions , 1990, Proceedings [1990] 31st Annual Symposium on Foundations of Computer Science.

[57]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[58]  박상용.  [경제학] 현시선호이론(Revealed Preference Theory) , 1980 .

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

[60]  Laurence A. Wolsey,et al.  Best Algorithms for Approximating the Maximum of a Submodular Set Function , 1978, Math. Oper. Res..