DPhil (PhD) Student in Computer Science

University of Oxford


I am Amartya Sanyal, currently a D.Phil(PhD) student at the Department of Computer Science at the University of Oxford where I am advised by Prof. Varun Kanade and Prof. Phil H.S. Torr. I completed by Bachelor Of Technology in Computer Science And Engineering from the Indian Institute of Technology, Kanpur in 2017.

Currently, my research interests span theoretical and empirical investigation on the reliability of modern deep learning methods in aspects of robustness and generalization in the presence of noise. In particular, I look at the importance of proper regularizations and representation learning that can help to effectively improve these properties. My research also looks at improving privacy, calibration and computational efficiency of deep learning methods.


  • Generalization
  • Robustness
  • Regularization


  • PhD in Computer Science, 2017-2021

    University of Oxford

  • BTech in Computer Science, 2013-2017

All Publications

Quickly discover relevant content by filtering publications.
How Benign is Benign Overfitting?
Progressive Skeletonization: Trimming more fat from a network at initialization
Calibrating Deep Neural Networks using Focal Loss
Robustness via Deep Low-Rank Representations
Optimizing Non-decomposable Measures with Deep Networks

Recent Posts



I have had the opportunity to visit a few places and carry out my research there. Here is a list of the places I have visited.

Research Visits

Conference Visits

  • Krakow, Poland Visisted Krakow to attend BESC 2017 where I delivered a 30 min oral presentation.
  • Buenos Aired Attended the Machine Learning Summer School in Buenos Aires.
  • Stockholm, Sweden Visited Stockholm in 2018 to attend COLT and ICML. (1 Poster + 2 Workshop Posters)
  • Long Beach, LA, US Visited Long Beach in 2019 to attend ICML. (1 Workshop Poster)
  • Addis Ababa, Ethiopia (Not really) Attended ICLR virtually. (1 Spotlight)

Non-Work Visits

  • Visited almost the entirety of India.
  • Hiked for a day in parts of Quebec around Val David, Val Morin.
  • Short trips to Paris, Edinburgh, Brussels, and Copenhagen.