Beyond Adaptive Submodularity: Approximation Guarantees of Greedy Policy with Adaptive Submodularity Ratio

We propose a new concept named adaptive submodularity ratio to study the greedy policy for sequential decision making. While the greedy policy is known to perform well for a wide variety of adaptive stochastic optimization problems in practice, its theoretical properties have been analyzed only for a limited class of problems. We narrow the gap between theory and practice by using adaptive submodularity ratio, which enables us to prove approximation guarantees of the greedy policy for a substantially wider class of problems. Examples of newly analyzed problems include important applications such as adaptive influence maximization and adaptive feature selection. Our adaptive submodularity ratio also provides bounds of adaptivity gaps. Experiments confirm that the greedy policy performs well with the applications being considered compared to standard heuristics.

[1]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

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

[3]  Andreas Krause,et al.  Sequential Information Maximization: When is Greedy Near-optimal? , 2015, COLT.

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

[5]  Xiaokui Xiao,et al.  Influence maximization: near-optimal time complexity meets practical efficiency , 2014, SIGMOD Conference.

[6]  Eric Balkanski,et al.  The adaptive complexity of maximizing a submodular function , 2018, STOC.

[7]  Zheng Wen,et al.  Adaptive Submodular Maximization in Bandit Setting , 2013, NIPS.

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

[9]  Volkan Cevher,et al.  Robust Maximization of Non-Submodular Objectives , 2018, AISTATS.

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

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

[12]  Ken-ichi Kawarabayashi,et al.  Optimal Budget Allocation: Theoretical Guarantee and Efficient Algorithm , 2014, ICML.

[13]  Noga Alon,et al.  Optimizing budget allocation among channels and influencers , 2012, WWW.

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

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

[16]  Andreas Krause,et al.  Near-Optimal Bayesian Active Learning with Noisy Observations , 2010, NIPS.

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

[18]  Ken-ichi Kawarabayashi,et al.  Adaptive Budget Allocation for Maximizing Influence of Advertisements , 2016, IJCAI.

[19]  Andreas Krause,et al.  Near Optimal Bayesian Active Learning for Decision Making , 2014, AISTATS.

[20]  Tengyuan Liang,et al.  Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP , 2017, ICML.

[21]  Sze Zheng Yong,et al.  Weak adaptive submodularity and group-based active diagnosis with applications to state estimation with persistent sensor faults , 2017, 2017 American Control Conference (ACC).

[22]  Ken-ichi Kawarabayashi,et al.  Optimal Pricing for Submodular Valuations with Bounded Curvature , 2016, AAAI.