Parthe Pandit
 |
Thakur Family Chair Assistant Professor
Center for Machine Intelligence and Data Science (C-MInDS)
Indian Institute of Technology, Bombay
email: pandit@iitb.ac.in
office: KR 320, Kanwal Rekhi building
contact: +91 22 2159 (IIT ext. 3776) |
About Me
I am a core faculty member at C-MInDS, IIT Bombay. Prior to joining IIT Bombay, I was a postdoc at HDSI, UCSD. I obtained a PhD in ECE and MS in Statistics both from UCLA, and a B.Tech + M.Tech dual degree in EE from IIT Bombay.
My current research focusses on understanding the generalization behaviour of interpolating machine learning models such as neural networks. I also develop fast and scalable algorithms for training kernel machines.
Students interested in working with me please read this note.
News
[Sept 2025] JMLR paper on the behaviour of kernel matrices in the quadratic asymptotic regime (arXiv)
[Sept 2025] Spotlight at NeurIPS 2025 on fast training of kernel machines (arXiv)
[Sept 2025] Sudhendu Ahir awarded the TCS fellowship (linkedin). Congratulations Sudhendu!
[May 2025] Oral at ICML 2025 on Emergence and Grokking in Kernel Machines (arXiv)
[Feb 2025] Paper on random feature maps for approximating the Laplacian kernel. (arXiv)
[Jan 2025] AISTATS 2025 paper on momentum for training of kernel machines. (PMLR)
[Dec 2024] I am honoured to receive the AI2050 Early Career Fellowship from Schmidt Sciences. (Forbes)
[Mar 2024] I was awarded the INSPIRE faculty fellowship by DST.
[Mar 2024] Science published our paper on the mechanism of feature learning in neural networks.