`

Timezone: »

 
Poster
A Universal Law of Robustness via Isoperimetry
Sebastien Bubeck · Mark Sellke

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @ Virtual #None
Classically, data interpolation with a parametrized model class is possible as long as the number of parameters is larger than the number of equations to be satisfied. A puzzling phenomenon in the current practice of deep learning is that models are trained with many more parameters than what this classical theory would suggest. We propose a theoretical explanation for this phenomenon. We prove that for a broad class of data distributions and model classes, overparametrization is {\em necessary} if one wants to interpolate the data {\em smoothly}. Namely we show that {\em smooth} interpolation requires $d$ times more parameters than mere interpolation, where $d$ is the ambient data dimension. We prove this universal law of robustness for any smoothly parametrized function class with polynomial size weights, and any covariate distribution verifying isoperimetry. In the case of two-layers neural networks and Gaussian covariates, this law was conjectured in prior work by Bubeck, Li and Nagaraj. We also give an interpretation of our result as an improved generalization bound for model classes consisting of smooth functions.

Author Information

Sebastien Bubeck (Microsoft Research)
Mark Sellke (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors