Mikhail Konobeev

2 accepted papers

2021

A Distribution-dependent Analysis of Meta Learning

Mikhail Konobeev, Ilja Kuzborskij, Csaba Szepesvari

ICML 2021spotlight

A key problem in the theory of meta-learning is to understand how the task distributions influence transfer risk, the expected error of a meta-learner on a new task drawn from the unknown task distribution. In this paper, focusing on fixed design linear regression with Gaussian noise and a Gaussian…

Cited by 5 Source ↗PDF ↗Scholar ↗

2021

Meta-Thompson Sampling

Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-Wei Hsu, Martin Mladenov, Craig Boutilier +1

ICML 2021spotlight

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several eff…

Cited by 84 Source ↗PDF ↗Scholar ↗