Depen Morwani

About

Depen Morwani is a 3rd year Ph.D. student at Harvard, advised by Boaz Barak and Sham Kakade. He is generally interested in optimization aspects of deep learning. Previously, he completed an internship at Microsoft Research under the guidance of Cyril Zhang and Adam Block, working on learning rate scheduling in deep learning. Morwani has also worked at Google Research as a Research Associate, under the guidance of Praneeth Netrapalli and Prateek Jain, exploring simplicity bias in deep networks.

Research Focus

Morwani is generally interested in optimization aspects of deep learning. His current research focuses on understanding the inductive bias/landscape of optimization algorithms in deep learning, and utilizing it for coming up with better (in terms of efficiency/speed/bias towards safe/fair/robust features) optimization algorithms.