My Publications

Feel free to refer my Google Scholar Profile as well.

1. Representation Learning Using a Single Forward Pass
   A Somasundaram, P Mishra, A Borthakur
   [Poster] Best poster award @ 15^th Annual Machine Learning Symposium at the New York Academy of Sciences

2. Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation Is Wasteful
   Martin Marek, Sanae Lotfi, Aditya Somasundaram, Andrew Gordon Wilson, Micah Goldblum (under Review)