About Me
I am a recent graduate of UC San Diego getting a bachellors degree in Computational Physics and a minor in Mathematics. I have a strong interest in the intersection of physics/mathematics and machine learning. My goal is to develop efficient machine learning models rooted in the underlying physical and mathematical principles the govern the world and their task.
I am currently taking a gap year in Zurich Switzerland, studying Datascience at ETH Zurich before starting my PhD the following year at Yale University in Elecrical & Computer Engineering.
I am interested in model compression, efficient deep learning, and the application of machine learning to scientific problems. I work on Quantization Aware training, pruning, and knowledge distillation to create efficient deep learning models.
Notable Papers
Neural Architecture Codesign for Fast Physics Applications
This paper presents a new hardware-aware neural architecture search pipeline for low latency deployment
wa-hls4ml: Benchmark and Surrogate Models for hls4ml Resource Estimation
Benchmark and dataset of over 680,000 synthesized neural networks to evaluate GNN- and transformer-based surrogate models predicting FPGA resource usage and latency