Leveraging Side Observations in Stochastic Bandits

This paper considers stochastic bandits with side observations, a model that accounts for both the exploration/exploitation dilemma and relationships between arms. In this setting, after pulling an arm i, the decision maker also observes the rewards for some other actions related to i. We will see that this model is suited to content recommendation in social networks, where users' reactions may be endorsed or not by their friends. We provide efficient algorithms based on upper confidence bounds (UCBs) to leverage this additional information and derive new bounds improving on standard regret guarantees. We also evaluate these policies in the context of movie recommendation in social networks: experiments on real datasets show substantial learning rate speedups ranging from 2.2x to 14x on dense networks.

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

[2]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[3]  Krishna P. Gummadi,et al.  On the evolution of user interaction in Facebook , 2009, WOSN '09.

[4]  Aurélien Garivier,et al.  Parametric Bandits: The Generalized Linear Case , 2010, NIPS.

[5]  David S. Johnson,et al.  Approximation algorithms for combinatorial problems , 1973, STOC.

[6]  Thomas P. Hayes,et al.  Stochastic Linear Optimization under Bandit Feedback , 2008, COLT.

[7]  Krishna P. Gummadi,et al.  Analyzing facebook privacy settings: user expectations vs. reality , 2011, IMC '11.

[8]  Martin Ester,et al.  A matrix factorization technique with trust propagation for recommendation in social networks , 2010, RecSys '10.

[9]  Shie Mannor,et al.  From Bandits to Experts: On the Value of Side-Observations , 2011, NIPS.

[10]  Csaba Szepesvári,et al.  –armed Bandits , 2022 .

[11]  John N. Tsitsiklis,et al.  Linearly Parameterized Bandits , 2008, Math. Oper. Res..

[12]  Csaba Szepesvári,et al.  Tuning Bandit Algorithms in Stochastic Environments , 2007, ALT.

[13]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[14]  H. Vincent Poor,et al.  Bandit problems with side observations , 2005, IEEE Transactions on Automatic Control.

[15]  T. L. Lai Andherbertrobbins.  Asymptotically Efficient Adaptive Allocation Rules , 1985 .

[16]  Guangdong Feng,et al.  A Tensor Based Method for Missing Traffic Data Completion , 2013 .

[17]  H. Robbins.  Some aspects of the sequential design of experiments , 1952 .

[18]  Deepayan Chakrabarti,et al.  Multi-armed bandit problems with dependent arms , 2007, ICML '07.

[19]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[20]  Sewoong Oh,et al.  A Gradient Descent Algorithm on the Grassman Manifold for Matrix Completion , 2009, ArXiv.