Online Improper Learning with an Approximation Oracle

We study the following question: given an efficient approximation algorithm for an optimization problem, can we learn efficiently in the same setting? We give a formal affirmative answer to this question in the form of a reduction from online learning to offline approximate optimization using an efficient algorithm that guarantees near optimal regret. The algorithm is efficient in terms of the number of oracle calls to a given approximation oracle – it makes only logarithmically many such calls per iteration. This resolves an open question by Kalai and Vempala, and by Garber. Furthermore, our result applies to the more general improper learning problems.

Authors

• Elad Hazan
• Wei Hu State Key Laboratory for Novel Software Technology, Nanjing University, China National Institute of Healthcare Data Science, Nanjing University, China
• Yuanzhi Li Carnegie Mellon University, Pittsburgh, PA, USA
• Zhiyuan Li Aalto University

Keywords

No keywords are indexed for this paper.