Timezone: »

Exploiting easy data in online optimization
Amir Sani · Gergely Neu · Alessandro Lazaric

Wed Dec 10 08:40 AM -- 09:05 AM (PST) @ Level 2, room 210

We consider the problem of online optimization, where a learner chooses a decision from a given decision set and suffers some loss associated with the decision and the state of the environment. The learner's objective is to minimize its cumulative regret against the best fixed decision in hindsight. Over the past few decades numerous variants have been considered, with many algorithms designed to achieve sub-linear regret in the worst case. However, this level of robustness comes at a cost. Proposed algorithms are often over-conservative, failing to adapt to the actual complexity of the loss sequence which is often far from the worst case. In this paper we introduce a general algorithm that, provided with a safe learning algorithm and an opportunistic benchmark, can effectively combine good worst-case guarantees with much improved performance on easy data. We derive general theoretical bounds on the regret of the proposed algorithm and discuss its implementation in a wide range of applications, notably in the problem of learning with shifting experts (a recent COLT open problem). Finally, we provide numerical simulations in the setting of prediction with expert advice with comparisons to the state of the art.

Author Information

Amir Sani (Centre d'Economie de la Sorbonne, CNRS)
Gergely Neu (Universitat Pompeu Fabra)
Alessandro Lazaric (Facebook Artificial Intelligence Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors