About Me
Hey! I'm Amit Saha, a third-year undergraduate student at Georgia Tech studying computer science and mathematics. If you'd like to reach out, find my contact information here.
Research: Broadly, I like working on theoretical problems with applications in fairness, safety, and privacy. More specifically, I like to exploit tools from
{information theory, high dimensional probability, algorithmic sampling}
as primitives to understand problems in
{statistical learning theory, deep learning},
usually under the constraint of differential privacy. Learn more about my current projects and previous work here.
Updates: I'll be visiting Harvard and OpenDP this summer, advised by Salil Vadhan! Incredibly excited to continue working on privacy and statistical learning theory!
Currently, I work under Pan Li, Andre Wibisono, and Ashia Wilson, and collaborate closely with Yinan Huang, Rongzhe Wei, Eli Chien, Jan Schuchardt, Vishwak Srinivasan, and Siddharth Mitra. I'm deeply grateful for the guidance and support I've received from them.
Outside of my main research interests, I am deeply invested in {systems for machine learning, AI safety, autoformalization for mathematics via language models}, although I do not actively work on research in these fields. To this end, I am a contributor to the Marin project, an active member of the AISI community at Georgia Tech, and regularly make use of autoformalization tools for my own (mathematical) research.
Academics: I credit much of my research to ideas first learnt in different classes at Georgia Tech. If you're interested, check out my coursework here.
Industry Experience: I spent two wonderful summers working at Adobe on the Camera Raw team as a machine learning research intern under Michelle Qi and David Franzen.
Everything else: At last — nonacademically — I enjoy making pizza, reading, and listening to music all the time.