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 in EE from IIT Bombay.
My current research focusses on understanding the generalization behaviour of interpolating machine learning models such as neural networks and kernel machines. I also develop training algorithms for large scale kernel machines.
I am an AI-2050 Early Career Fellow by Schmidt Sciences. This fellowship comes with an unrestricted research grant of 300,000 USD. Thank you, Schmidt Sciences! Read more about my project here.
Students interested in working with me please read this note.
News
[Mar 2025] C-MInDS is growing! (minds.iitb.ac.in/people/core-faculty)
[Feb 2025] Paper on random feature maps for approximating the Laplacian kernel. (arXiv:2502.15575)
[Jan 2025] Paper accepted at AISTATS 2025. (OpenReview)
[Dec 2024] I am honoured to receive the AI2050 Early Career Fellowship from Schmidt Sciences. (Forbes)
[Nov 2024] We have a massive speed-up for EigenPro algorithms to train large kernel machines, linear memory and linear time! (arXiv:2411.16658)
[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.
[Jan 2024] Paper accepted at AISTATS 2024 'On the Nyström Approximation for Preconditioning in Kernel Machines.'
[Nov 2023] Zhichao Wang presented our contributed talk at DeepMath 2023 based on our work 'Quadratic Approximation of Random Inner-Product Kernel Matrices.’
[Nov 2023] I am now with C-MInDS at IIT Bombay.