Graduate Student at Stanford University
I am a fifth-year Ph.D. student at the Stanford University Institute for Computational and Mathematical Engineering (ICME). I am very fortunate to be advised by Chris Ré. I earned my bachelor's degrees in mathematics and computer science from Cornell University.
I am interested in the theoretical and practical development of optimization methods for machine learning.
No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems. N. Sohoni, J. Dunnmon, G. Angus, A. Gu, C. Ré. To appear in Conference on Neural Information Processing Systems (NeurIPS), 2020.
Near-Optimal Methods for Minimizing Star-Convex Functions and Beyond. O. Hinder, A. Sidford, N. Sohoni. In Conference on Learning Theory (COLT), 2020.
Ivy: Instrumental Variable Synthesis for Causal Inference. Z. Kuang, F. Sala, N. Sohoni, S. Wu, A. Cordova-Palomera, J. Dunnmon, J. Priest, C. Ré. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
Kaleidoscope: An Efficient, Learnable Representation For All Structured Linear Maps. T. Dao, N. Sohoni, A. Gu, M. Eichhorn, A. Blonder, M. Leszczynski, A. Rudra, C. Ré. In International Conference on Learning Representations (ICLR), 2020. (Spotlight)
Low-Memory Neural Network Training: A Technical Report. N. Sohoni, C. Aberger, M. Leszczynski, J. Zhang, C. Ré. arXiv, 2019. (Preprint)
DeepHeart: Semi-Supervised Sequence Learning for Cardiovascular Risk Prediction. B. Ballinger, J. Hsieh, A. Singh, N. Sohoni, J. Wang, G. Tison, G. Marcus, J. Sanchez, C. Maguire, J. Olgin, M. Pletcher. In AAAI Conference on Artificial Intelligence, 2018.