Search Results for author: Darshil Doshi

Found 2 papers, 1 papers with code

AutoInit: Automatic Initialization via Jacobian Tuning

no code implementations27 Jun 2022 Tianyu He, Darshil Doshi, Andrey Gromov

Good initialization is essential for training Deep Neural Networks (DNNs).

Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications

1 code implementation23 Nov 2021 Darshil Doshi, Tianyu He, Andrey Gromov

We introduce \emph{partial Jacobians} of a network, defined as derivatives of preactivations in layer $l$ with respect to preactivations in layer $l_0\leq l$.

Cannot find the paper you are looking for? You can Submit a new open access paper.