Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
Abstract: We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an N-dimensional space and belongs to a ...
We study stochastic linear optimization problem with bandit feed- back. The set of arms take values in an N-dimensional space and.
The key insight is that for a polyhedron the optimal arm is robust to small perturbations in the reward function, Consequently, a greedily selected arm is ...
Sep 26, 2015 · Abstract:We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an N-dimensional space and ...
Request PDF | On Mar 1, 2016, Manjesh K. Hanawal and others published Efficient algorithms for linear polyhedral bandits | Find, read and cite all the ...
We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an N-dimensional space and belongs to a bounded ...
Efficient algorithms for linear polyhedral bandits · M. HanawalAmir LeshemVenkatesh Saligrama. Computer Science, Mathematics. 2016 IEEE International Conference ...
EFFICIENT ALGORITHMS FOR LINEAR POLYHEDRAL BANDITS. Authors: Manjesh Kumar Hanawal, Indian Institute of Technology Bombay, India; Amir Leshem, Bar-Ilan ...
Fingerprint. Dive into the research topics of 'Efficient algorithms for linear polyhedral bandits'. Together they form a unique fingerprint.
Sep 26, 2015 · We study stochastic linear optimization problem with bandit feedback. The set of arms take values in an $N$-dimensional space and belong to ...