A law of robustness and the importance of overparametrization in deep learning
- Sebastien Bubeck | Microsoft Research
Microsoft Research Senior Principal Researcher Sebastien Bubeck answers several questions about the NeurIPS 2021 paper, “A Universal Law of Robustness via Isoperimetry.” He discusses what overparametrization is, the law of robustness, and how these two concepts can impact the future of large deep neural network research.
Read the full paper-
-
Sébastien Bubeck
Vice President, Microsoft GenAI
-
-
Watch Next
-
-
-
-
-
-
-
-
Physics and information theory of generative diffusion
- Luca Ambrogioni
-
-
Upper Bound 2024: Towards Human-Centered AI in AAA Video Game
- Raluca Georgescu