Neil Rohit Mallinar
UC San Diego. Halıcıoğlu Data Science Institute. nmallina@ucsd.edu.
Currently seeking an office :)
10100 Hopkins Dr
San Diego, CA 92093
I’m pursuing my PhD at UC San Diego, advised by Misha Belkin. I am also a Research Fellow at The Broad Institute where I am adivsed by Anthony Philippakis. For a full list of publications, see Google Scholar.
My research focuses on understanding deep learning, both theoretically and practically. In the past, I studied: benign overfitting in neural networks and kernel regression; and calibration in neural networks as it relates to generalization. My current research focuses on spectral properties of De Bruijn graphs, high-dimensional linear regression under distribution shifts, and, most recently, studying phenomena such as grokking and in-context learning with transformers, fully connected networks, and kernels.
my life in four days
Sep 28, 2020 | Started my PhD at UC San Diego |
---|---|
Aug 1, 2019 | Joined Pryon Inc in Brooklyn |
Aug 23, 2016 | Moved to New York, started at IBM Watson |
May 18, 2016 | Got my Bachelor’s from Johns Hopkins University |
news
selected publications
-
In 36th Conference on Neural Information Processing Systems (NeurIPS 2022) Jul 2022
-
2022 International Conference on Machine Learning (Workshop on Distribution-Free Uncertainty Quantification) Oct 2022
-
In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) Nov 2020
-
International Conference on Learning Representations 2019
-
Proceedings of the AAAI Conference on Artificial Intelligence Dec 2018
-
Astronomy and Computing Jul 2017