Course: Graphs in Machine Learning, by Michal VALKO
This was a project to validate the course. The aim was to implement understand and implement several optimization algorithms from the litterature in a combinatorial semi bandit setting and to test and compare these on diverse issues.
Regrets In Online Combinatorial Optimization, J-Y Audibert, S Bubeck, G Lugosi
Importance Weighting Without Importance Weights: An Efficient Algorithm For Combinatorial Semi Bandits, G Neu, G Bartok
Tight Regret bounds For Stochastic Combinatorial Semi Bandits B Kveton, A Ashkan, Z wen, C Szepesvari