Rajarshi Saha
Ph.D. Student, Stanford University
I am a final year Ph.D. student in Electrical Engineering at Stanford University. I am fortunate to be co-advised by Mert Pilanci and Andrea Goldsmith. My research interests broadly lie in identifying and addressing problems related to distributed optimization over resource-constrained edge devices. I enjoy understanding problems in this domain from a theoretical perspective, investigating notions of optimality, and designing theoretically-backed practical algorithms.
Prior to joining Stanford, I completed my Bachelors' and Masters' from Indian Institute of Technology (IIT) Kharagpur, with a major in Electronics and Electrical Communications Engineering, a minor in Computer Science, and a micro-specialization in Embedded Wireless Systems. During my time there, I worked with my advisor Mrityunjoy Chakraborty on topics of MIMO Radar Imaging which received the Best Undergraduate Thesis Award. I was also the recipient of the Prime Minister of India Gold Medal for being the class valedictorian.
Research interests: Optimization, Machine Learning, Wireless Communications, Signal Processing.
Email: rajsaha [at] stanford [dot] edu
Recent News:
[Dec 2023] Presenting our work "Matrix Compression via Randomized Low Rank and Low Precision Factorization" at NeurIPS 2023, New Orleans. Our new matrix factorization method that exploits the approximate low-rank structure (found in several real-world matrices such as LLM weight matrices) to obtain low-rank factors whose entries are quantized to low-precision.
[June 2023] Presenting our work "Collaborative Mean Estimation over Intermittently Connected Networks with Peer-To-Peer Privacy" at ISIT 2023, Taipei, Taiwan.
[June 2023] Presenting our work "Low Precision Representations for High Dimensional Models" at ICASSP 2023, Rhodes Island, Greece.