Scholar
Kanan Gupta
Google Scholar ID: jYcRZO4AAAAJ
University of Pittsburgh
Citations & Impact
Citations
13
H-index
2
i10-index
0
Publications
3
Co-authors
2
list available
Publications
Resume (English only)
Academic Achievements
- Publications: 1. Nesterov acceleration despite very noisy gradients (NeurIPS 2024); 2. Nesterov acceleration in benignly non-convex landscapes (ICLR 2025, Spotlight); 3. Momentum-based minimization of the Ginzburg-Landau functional on Euclidean spaces and graphs (Preprint, 2025); Reviewer experience: ICLR 2025 reviewer, Journal of Machine Learning Research (JMLR) reviewer.
Research Experience
- Fourth-year PhD student focusing on optimization algorithms in machine learning; Started PhD at Texas A&M University before moving to Pitt with advisor.
Education
- PhD student, Department of Mathematics, University of Pittsburgh, Advisor: Dr. Stephan Wojtowytsch; Previously at Texas A&M University; Undergraduate degree from Ashoka University, major in Mathematics, minor in Computer Science; Completed a one-year postgraduate diploma in research at Ashoka University, writing an expository thesis on K-Theory and C*-Algebras.
Background
- Research interests: mathematics of machine learning, specifically optimization algorithms; Areas of expertise: intersection of mathematics and computer science, such as using ML for solving PDEs and automated theorem proving.
Miscellany
- Email: kanan.g@pitt.edu; Office: 623 Thackeray Hall; Department: Department of Mathematics, University of Pittsburgh.
