← Search

Khan Mohammad Emtiyaz

2 accepted papers

2021

Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning

ICML 2021spotlight

Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties. Instead, most approaches rely on validation data, which may not be readily available. In this work, we present a scalable marginal-likelihood estimation method to select…

2021

Tractable structured natural-gradient descent using local parameterizations

ICML 2021spotlight

Natural-gradient descent (NGD) on structured parameter spaces (e.g., low-rank covariances) is computationally challenging due to difficult Fisher-matrix computations. We address this issue by using \emph{local-parameter coordinates} to obtain a flexible and efficient NGD method that works well for a…

Cited by 38SourcePDFScholar