Christopher Tosh — accepted AI-conference papers

2021

Bayesian decision-making under misspecified priors with applications to meta-learning

Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miroslav Dudík +1

NeurIPS 2021spotlight

Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The choice of prior in these algorithms offers flexibility to encode domain knowledge but can also lead to poor performance…

Cited by 62 Source ↗PDF ↗Scholar ↗

2020

Diameter-based Interactive Structure Discovery

Christopher Tosh, Daniel Hsu

AISTATS 2020poster

We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta for intera…

Cited by 4 Source ↗PDF ↗Scholar ↗

2018

Interactive Structure Learning with Structural Query-by-Committee

Christopher Tosh, Sanjoy Dasgupta

NeurIPS 2018spotlight

In this work, we introduce interactive structure learning, a framework that unifies many different interactive learning tasks. We present a generalization of the query-by-committee active learning algorithm for this setting, and we study its consistency and rate of convergence, both theoretically an…

Cited by 8 Source ↗PDF ↗Scholar ↗

2017

Diameter-Based Active Learning

Christopher Tosh, Sanjoy Dasgupta

ICML 2017poster

To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically de…

Cited by 35 Source ↗PDF ↗Scholar ↗

2016

Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends

Christopher Tosh

ICML 2016poster

Alternating Gibbs sampling is a modification of classical Gibbs sampling where several variables are simultaneously sampled from their joint conditional distribution. In this work, we investigate the mixing rate of alternating Gibbs sampling with a particular emphasis on Restricted Boltzmann Machine…

Cited by 18 Source ↗PDF ↗Scholar ↗