Henry Chai

2 accepted papers

2020

BINOCULARS for efficient, nonmyopic sequential experimental design

Shali Jiang, Henry Chai, Javier Gonzalez, Roman Garnett

ICML 2020poster

Finite-horizon sequential experimental design (SED) arises naturally in many contexts, including hyperparameter tuning in machine learning among more traditional settings. Computing the optimal policy for such problems requires solving Bellman equations, which are generally intractable. Most existin…

Cited by 61 Source ↗PDF ↗code ↗Scholar ↗

2019

Automated Model Selection with Bayesian Quadrature

Henry Chai, Jean-Francois Ton, Michael A. Osborne, Roman Garnett

ICML 2019oral

We present a novel technique for tailoring Bayesian quadrature (BQ) to model selection. The state-of-the-art for comparing the evidence of multiple models relies on Monte Carlo methods, which converge slowly and are unreliable for computationally expensive models. Although previous research has show…

Cited by 16 Source ↗PDF ↗Scholar ↗