Exploiting easy data in online optimization

Amir Sani 1 Gergely Neu 1 Alessandro Lazaric 1
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal, Inria Lille - Nord Europe
Abstract : 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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01079428
Contributor : Gergely Neu <>
Submitted on : Saturday, November 1, 2014 - 10:59:51 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Long-term archiving on : Monday, February 2, 2015 - 5:01:06 PM

File

SNL14.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01079428, version 1

Citation

Amir Sani, Gergely Neu, Alessandro Lazaric. Exploiting easy data in online optimization. Advances in Neural Information Processing 27, Dec 2014, Montreal, Canada. ⟨hal-01079428⟩

Share

Metrics

Record views

320

Files downloads

144