Scholar
Krishnakumar Balasubramanian
Google Scholar ID: uuts9CAAAAAJ
University of California, Davis
Citations & Impact
Citations
1,626
H-index
24
i10-index
38
Publications
20
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- On the Structure of Stationary Solutions to McKean-Vlasov Equations with Applications to Noisy Transformers, 2025.
- Dense associative memory on the Bures-Wasserstein space, 2025.
- Finite-Dimensional Gaussian Approximation for Deep Neural Networks: Universality in Random Weights, Bernoulli (under major revision), 2025.
- Dense Associative Memory with Epanechnikov energy, NeurIPS (spotlight presentation), 2025.
- In-context Learning for Mixture of Linear Regressions: Existence, Generalization and Training Dynamics, Transactions on Machine Learning Research (TMLR), 2025.
- Transformers Handle Endogeneity in In-Context Linear Regression, ICLR, 2025.
- From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression, Transactions on Machine Learning Research (TMLR), 2024.
- Gaussian random field approximation via Stein's method with applications to wide random neural networks, Applied and Computational Harmonic Analysis, 2024.
- More papers listed in the original document.
Research Experience
- No specific research experience information provided.
Education
- No specific educational background information provided.
Background
- Associate Professor in the Department of Statistics, Graduate Group in Applied Mathematics, and Graduate Program in Electrical and Computer Engineering at the University of California, Davis. Research interests include deep learning, foundation models, etc.
Miscellany
- Support: NSF and CeDAR grants. Office: MSB 4109. Email: kbala@ucdavis.edu.
Co-authors