Gains and Losses are Fundamentally Different in Regret Minimization: The Sparse Case
Résumé
We demonstrate that, in the classical non-stochastic regret minimization problem with d decisions, gains and losses to be respectively maximized or minimized are fundamentally different. Indeed, by considering the additional sparsity assumption (at each stage, at most s decisions incur a nonzero outcome), we derive optimal regret bounds of different orders. Specifically, with gains, we obtain an optimal regret guarantee after T stages of order √ T log s, so the classical dependency in the dimension is replaced by the sparsity size. With losses, we provide matching upper and lower bounds of order T s log(d)/d, which is decreasing in d. Eventually, we also study the bandit setting, and obtain an upper bound of order T s log(d/s) when outcomes are losses. This bound is proven to be optimal up to the logarithmic factor log(d/s).
Origine | Fichiers éditeurs autorisés sur une archive ouverte |
---|---|
Licence |