no code implementations • 25 Oct 2023 • Noam Levi, Alon Beck, Yohai Bar-Sinai
Grokking is the intriguing phenomenon where a model learns to generalize long after it has fit the training data.
no code implementations • 3 Apr 2023 • Theo Jules, Gal Brener, Tal Kachman, Noam Levi, Yohai Bar-Sinai
The training of neural networks is a complex, high-dimensional, non-convex and noisy optimization problem whose theoretical understanding is interesting both from an applicative perspective and for fundamental reasons.
2 code implementations • 11 Apr 2020 • Jiawei Zhuang, Dmitrii Kochkov, Yohai Bar-Sinai, Michael P. Brenner, Stephan Hoyer
The computational cost of fluid simulations increases rapidly with grid resolution.
Computational Physics Disordered Systems and Neural Networks Fluid Dynamics
3 code implementations • 15 Aug 2018 • Yohai Bar-Sinai, Stephan Hoyer, Jason Hickey, Michael P. Brenner
Many problems in theoretical physics are centered on representing the behavior of a physical theory at long wave lengths and slow frequencies by integrating out degrees of freedom which change rapidly in time and space.
Disordered Systems and Neural Networks Computational Physics
1 code implementation • Science Advances (to appear) 2019 • Jordan Hoffmann, Yohai Bar-Sinai, Lisa Lee, Jovana Andrejevic, Shruti Mishra, Shmuel M. Rubinstein, Chris H. Rycroft
Machine learning has gained widespread attention as a powerful tool to identify structure in complex, high-dimensional data.
Soft Condensed Matter