Timezone: »

 
Poster
Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds and Benign Overfitting
Frederic Koehler · Lijia Zhou · Danica J. Sutherland · Nathan Srebro

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »
We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interpolators in an arbitrary hypothesis class in terms of the class’s Gaussian width. Applying the generic bound to Euclidean norm balls recovers the consistency result of Bartlett et al. (2020) for minimum-norm interpolators, and confirms a prediction of Zhou et al. (2020) for near-minimal-norm interpolators in the special case of Gaussian data. We demonstrate the generality of the bound by applying it to the simplex, obtaining a novel consistency result for minimum $\ell_1$-norm interpolators (basis pursuit). Our results show how norm-based generalization bounds can explain and be used to analyze benign overfitting, at least in some settings.
Keywords: Theory

Author Information

Frederic Koehler (MIT)
Lijia Zhou (University of Chicago)
Danica J. Sutherland (University of British Columbia)
Nathan Srebro (University of Toronto)

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

More from the Same Authors