Search papers, labs, and topics across Lattice.
Inria Lille, ENS Paris-Saclay Vianney Perchet, ENSAE & Criteo AI Lab, DeepMind Paris
Google DeepMind1
0
1
Forget sub-Gaussian assumptions: this semi-bandit algorithm adapts to the true covariance structure of outcomes, leading to tighter regret bounds and better performance.
