Dhruva's Dumb Website


Hi! I’m Dhruva, a third-year physics graduate student at UC Berkeley. I’m interested in the mechanisms that underpin systems that learn from an external signal, and I study deep neural networks as a scientifically-accessible model of such systems. I’m especially interested the large-learning-rate phenomena associated with feature learning and I hope to understand why deep learning is more sample-efficient than classical machine learning techniques, like kernel machines.

Before moving to the bay area, I lived in Texas and studied physics, astronomy, and computer science at UT Austin. In my free time, I enjoy hanging out with friends, cooking, playing chess, messing around with synthesizers, making generative art, or thinking about literally anything other than whatever pressing deadline is approaching.


Apr 30, 2024 My tutorial deriving the lazy (NTK) and rich (\(\mu\)P) regimes is on arxiv, check it out!
Jan 16, 2024 Our paper showing that More Is Better in modern ML will be at ICLR 2024 :)
May 29, 2023 Our paper explaining generalization in kernel machines was accepted in TMLR!
May 6, 2022 I won the Teaching Effectiveness Award! :sunglasses: WOO!!!!
Mar 22, 2022 I won the Outstanding Graduate Student Instructor award! :)))