Weakly Submodular Function Maximization Using Local Submodularity Ratio

Weak submodularity is a natural relaxation of the diminishing return property, which is equivalent to submodularity. Weak submodularity has been used to show that many (monotone) functions that arise in practice can be efficiently maximized with provable guarantees. In this work we introduce two natural generalizations of weak submodularity for non-monotone functions. We show that an efficient randomized greedy algorithm has provable approximation guarantees for maximizing these functions subject to a cardinality constraint. We then provide a more refined analysis that takes into account that the weak submodularity parameter may change (sometimes improving) throughout the execution of the algorithm. This leads to improved approximation guarantees in some settings. We provide applications of our results for monotone and non-monotone maximization problems.

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

[2]  A. Borodin.  A Proportionally Submodular Functions , 2015 .

[3]  Alexandros G. Dimakis,et al.  Scalable Greedy Feature Selection via Weak Submodularity , 2017, AISTATS.

[4]  Amin Karbasi,et al.  Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy? , 2017, ICML.

[5]  Joseph Naor,et al.  A Unified Continuous Greedy Algorithm for Submodular Maximization , 2011, 2011 IEEE 52nd Annual Symposium on Foundations of Computer Science.

[6]  Alexandros G. Dimakis,et al.  Restricted Strong Convexity Implies Weak Submodularity , 2016, The Annals of Statistics.

[7]  Vahab S. Mirrokni,et al.  Maximizing Nonmonotone Submodular Functions under Matroid or Knapsack Constraints , 2009, SIAM J. Discret. Math..

[8]  Ben Taskar,et al.  Near-Optimal MAP Inference for Determinantal Point Processes , 2012, NIPS.

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

[10]  Refael Hassin,et al.  Approximation algorithms for maximum dispersion , 1997, Oper. Res. Lett..

[11]  Zoubin Ghahramani,et al.  Scaling the Indian Buffet Process via Submodular Maximization , 2013, ICML.

[12]  Abhimanyu Das,et al.  Submodular meets Spectral: Greedy Algorithms for Subset Selection, Sparse Approximation and Dictionary Selection , 2011, ICML.

[13]  Yuli Ye,et al.  Max-Sum diversification, monotone submodular functions and dynamic updates , 2012, PODS '12.

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

[15]  Huy L. Nguyen,et al.  Constrained Submodular Maximization: Beyond 1/e , 2016, 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS).

[16]  S. S. Ravi,et al.  Heuristic and Special Case Algorithms for Dispersion Problems , 1994, Oper. Res..

[17]  Jan Vondrák,et al.  Submodular maximization by simulated annealing , 2010, SODA '11.

[18]  Sreenivas Gollapudi,et al.  Diversifying search results , 2009, WSDM '09.

[19]  Benjamin E. Birnbaum,et al.  An Improved Analysis for a Greedy Remote-Clique Algorithm Using Factor-Revealing LPs , 2007, Algorithmica.

[20]  Jan Vondrák,et al.  Symmetry and Approximability of Submodular Maximization Problems , 2009, 2009 50th Annual IEEE Symposium on Foundations of Computer Science.

[21]  Allan Borodin,et al.  Weakly Submodular Functions , 2014, ArXiv.

[22]  Amin Karbasi,et al.  Submodular Maximization Beyond Non-negativity: Guarantees, Fast Algorithms, and Applications , 2019, ICML.

[23]  Evaggelia Pitoura,et al.  Search result diversification , 2010, SGMD.

[24]  Rishabh K. Iyer,et al.  Learning Mixtures of Submodular Functions for Image Collection Summarization , 2014, NIPS.

[25]  Aaron Roth,et al.  Constrained Non-monotone Submodular Maximization: Offline and Secretary Algorithms , 2010, WINE.

[26]  Niv Buchbinder,et al.  Constrained Submodular Maximization via a Non-symmetric Technique , 2016, Math. Oper. Res..

[27]  William Stafford Noble,et al.  Choosing non‐redundant representative subsets of protein sequence data sets using submodular optimization , 2018, Proteins.

[28]  Manuel Gomez-Rodriguez,et al.  Non-submodular Function Maximization subject to a Matroid Constraint, with Applications , 2018 .

[29]  Uriel Feige,et al.  Welfare maximization and the supermodular degree , 2013, ITCS '13.

[30]  Baharan Mirzasoleiman,et al.  Fast Constrained Submodular Maximization: Personalized Data Summarization , 2016, ICML.

[31]  Benjamin E. Birnbaum,et al.  An Improved Analysis for a Greedy Remote-Clique Algorithm Using Factor-Revealing LPs , 2006, Algorithmica.

[32]  Andreas Krause,et al.  Guarantees for Greedy Maximization of Non-submodular Functions with Applications , 2017, ICML.

[33]  F. Bruce Shepherd,et al.  Beyond Submodular Maximization via One-Sided Smoothness , 2019, SODA.

[34]  Wei Chen,et al.  Capturing Complementarity in Set Functions by Going Beyond Submodularity/Subadditivity , 2019, ITCS.

[35]  Abhimanyu Das,et al.  Approximate Submodularity and its Applications: Subset Selection, Sparse Approximation and Dictionary Selection , 2018, J. Mach. Learn. Res..

[36]  Alexandros G. Dimakis,et al.  Streaming Weak Submodularity: Interpreting Neural Networks on the Fly , 2017, NIPS.

[37]  Hui Lin,et al.  Multi-document Summarization via Budgeted Maximization of Submodular Functions , 2010, NAACL.

[38]  Yaron Singer,et al.  Maximization of Approximately Submodular Functions , 2016, NIPS.