Nikola B. Kovachki
Los Angeles, CA
nkovachki (at) nvidia (dot) com
I am research scientist at NVIDIA Research (NVR) working on machine learning methods for the physical sciences in theory and practice. I obtained my Ph.D. in applied and computational mathematics from Caltech in 2022 under the supervision of Prof. Andrew M. Stuart. Previously, I received a B.Sc. in mathematics from Caltech in 2016. I am a recipient of the 2020 Amazon AI4Science Fellowship, and some of my work has been featured in popular science magazines: MIT Technology Review, Quanta Magazine.
My research interest lie at the intersection of approximation theory, numerical analysis, and machine learning. Particularly, I work on the design and analysis of efficient approximation methods for forwards and inverse problems in PDEs, measure transport methods for sampling in high dimensions, and the blending of data and physics into machine learning models.
news
Oct 26, 2023 | I was a panelist at InterPACK 2023 in the session on AI for the Thermal Science Community. Thank you Yoonjin Won for the invitation! |
---|---|
Oct 14, 2023 | I gave a talk on Diffusion Models in Infinite Dimensions at SIAM PNW4 in the minisymposium on Scientific Machine Learning. Thank you Alex Hsu for the invitation! |
Aug 28, 2023 | I gave a talk on Diffusion Models in Infinite Dimensions at ICIAM 2023 in the minisymposium on Theoretical foundations and algorithmic innovation in operator learning. Thank you Jakob Zech for the invitation! |