Scholar
Parthe Pandit
Google Scholar ID: gp_Gdr8AAAAJ
Thakur Family Chair Assistant Professor @ IIT Bombay
Citations & Impact
Citations
636
H-index
12
i10-index
13
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- 1. [Sept 2025] JMLR paper on the behaviour of kernel matrices in the quadratic asymptotic regime (arXiv).
- 2. [Sept 2025] Spotlight at NeurIPS 2025 on fast training of kernel machines (arXiv).
- 3. [May 2025] Oral at ICML 2025 on Emergence and Grokking in Kernel Machines (arXiv).
- 4. [Feb 2025] Paper on random feature maps for approximating the Laplacian kernel (arXiv).
- 5. [Jan 2025] AISTATS 2025 paper on momentum for training of kernel machines (PMLR).
- 6. [Dec 2024] Received the AI2050 Early Career Fellowship from Schmidt Sciences (Forbes).
- 7. [Mar 2024] Awarded the INSPIRE faculty fellowship by DST.
- 8. [Mar 2024] Science published our paper on the mechanism of feature learning in neural networks.
Research Experience
- Was a postdoc at HDSI, UCSD before joining IIT Bombay.
Education
- PhD in ECE from UCLA, MS in Statistics from UCLA, B.Tech + M.Tech dual degree in EE from IIT Bombay.
Background
- Core faculty member at C-MInDS, IIT Bombay. Research focuses on understanding the generalization behavior of interpolating machine learning models such as neural networks and developing fast and scalable algorithms for training kernel machines.
Miscellany
- Contact: email pandit@iitb.ac.in, office KR 320, Kanwal Rekhi building, phone +91 22 2159 (IIT ext. 3776)
