Monthly Archives: August 2016

Kernel-based methods for convex bandits, part 3

(This post absolutely requires to have read Part 1 and Part 2.) A key assumption at the end of Part 1 was that, after rescaling space so that the current exponential weights distribution is isotropic, one has (1)   for … Continue reading

Posted in Optimization, Theoretical Computer Science | Comments Off on Kernel-based methods for convex bandits, part 3

Kernel-based methods for convex bandits, part 2

The goal of this second lecture is to explain how to do the variance calculation we talked about at the end of Part 1 for the case where the exponential weights distribution is non-Gaussian. We will lose here a factor … Continue reading

Posted in Optimization, Theoretical Computer Science | Comments Off on Kernel-based methods for convex bandits, part 2

Kernel-based methods for bandit convex optimization, part 1

A month ago Ronen Eldan, Yin Tat Lee and myself posted our latest work on bandit convex optimization. I’m quite happy with the result (first polynomial time method with poly(dimension)-regret) but I’m even more excited by the techniques we developed. Next … Continue reading

Posted in Optimization, Theoretical Computer Science | Comments Off on Kernel-based methods for bandit convex optimization, part 1