Akshunna S. Dogra — accepted AI-conference papers

2022

Universality of Winning Tickets: A Renormalization Group Perspective

William T Redman, Tianlong Chen, Zhangyang Wang, Akshunna S. Dogra

ICML 2022spotlight

Foundational work on the Lottery Ticket Hypothesis has suggested an exciting corollary: winning tickets found in the context of one task can be transferred to similar tasks, possibly even across different architectures. This has generated broad interest, but methods to study this universality are la…

Cited by 7 Source ↗PDF ↗Scholar ↗

2020

Optimizing Neural Networks via Koopman Operator Theory

Akshunna S. Dogra, William Redman

NeurIPS 2020poster

Koopman operator theory, a powerful framework for discovering the underlying dynamics of nonlinear dynamical systems, was recently shown to be intimately connected with neural network training. In this work, we take the first steps in making use of this connection. As Koopman operator theory is a li…

Cited by 75 Source ↗PDF ↗code ↗Scholar ↗