3 accepted papers
We study a new non-stochastic federated multiarmed bandit problem with multiple agents collaborating via a communication network. The losses of the arms are assigned by an oblivious adversary that specifies the loss of each arm not only for each time step but also for each agent, which we call doubl…
Combinatorial optimization problems with parameters to be predicted from side information are commonly seen in a variety of problems during the paradigm shift from reactive decision making to proactive decision making. Due to the misalignment between the continuous prediction results and the discret…
Finding an optimal matching in a weighted graph is a standard combinatorial problem. We consider its semi-bandit version where either a pair or a full matching is sampled sequentially. We prove that it is possible to leverage a rank-1 assumption on the adjacency matrix to reduce the sample complexit…