Ph.D. candidate in Electrical and Computer Engineering
University of Wisconsin–Madison
I am currently a Ph.D. candidate in the Department of Electrical and Computer Engineering at the University of Wisconsin–Madison, advised by Prof. Kangwook Lee and Prof. Robert D. Nowak. Before coming to Madison, I received my B.S. in Electrical and Computer Engineering from Rutgers University, where I was advised by Prof. Waheed U. Bajwa.
For more about my experiences, please check out my CV.
My research interests span the theoretical and practical aspects of signal processing and machine learning. I focus on bridging theory and practice in deep learning by developing theory for modern paradigms such as multi-task learning and implicit neural representations, and using these insights to guide the design of practical systems. More recently, I have become interested in the foundations of large language model pretraining, including optimization dynamics, memorization, and generalization in large-scale models.
We show that when a neural network is trained on many tasks at once, it behaves much more predictably and produces a unique, smooth solution — similar to classical kernel methods. In contrast, training on a single task can lead to many very different solutions, even when they fit the data equally well.
We introduce a variation space framework that explains how multi-output ReLU networks share structure across tasks in multi-task learning. This leads to principled methods for improving generalization and compressing networks without sacrificing performance.
We show that standard ReLU activations yield an ill-conditioned loss landscape for INR problems. We then propose a B-spline wavelet–inspired modification to ReLU and demonstrate its effectiveness on standard INR tasks. Finally, we connect these findings to my prior work on measuring function regularity for efficient hyperparameter selection.
