I am a second year PhD student at Tulane University, working with Prof. Jihun Hamm. My current research is related to developing a method for solving large-scale bilevel optimization problems that appear in machine learning. Some of the important applications include hyperparameter optimization, few-shot learning, importance learning and training-data poisoning. I also work on understanding the limitation of machine learning models and am developing a method to make models robust to train and test-time attacks.
I completed my Masters in Computer Science from The Ohio State University under the guidance of Prof. Jihun Hamm and Prof. Mikhail Belkin where I worked on combining active learning and semi-supervised learning to speed up interactive image retrieval.
I am interested in large scale bilevel optimization and adversarial machine learning problems. I'm also very interested in understanding the problem of generalization in modern machine learning.
- “Penalty Method for Inversion-Free Deep Bilevel Optimization”. Code
Akshay Mehra, Jihun Hamm.
- “Fast Interactive Image Retrieval using large-scale unlabeled data”.
Akshay Mehra, Jihun Hamm and Mikhail Belkin.
- “Machine vs Machine: Minimax-Optimal Defense Against Adversarial Examples”.
Jihun Hamm and Akshay Mehra.