Depen Morwani
Scholar

Depen Morwani

Google Scholar ID: vOngxFUAAAAJ
Harvard University
Machine Learning TheoryTheoretical Deep Learning
Citations & Impact
All-time
Citations
262
 
H-index
8
 
i10-index
8
 
Publications
16
 
Co-authors
1
list available
Resume (English only)
Research Experience
  • Spent a year as a Research Associate at Google Research India, working with Praneeth Netrapalli and Prateek Jain on exploring the simplicity bias induced by gradient descent.
Education
  • Completed Masters from IIT Madras under the guidance of Harish Guruprasad, working on understanding the implications of weight normalization. Currently a PhD student at Harvard, advised by Boaz Barak and Sham Kakade.
Background
  • A 3rd year PhD student in the ML Foundations group at Harvard, broadly interested in optimization and generalization aspects of deep learning. Current research focuses on understanding the inductive bias of optimization algorithms in deep learning and utilizing it for better (in terms of efficiency/speed/bias towards safe/fair/robust features) optimization algorithms.
Co-authors
1 total