1.9k citations
- University of ChicagoUS60 papers
- Microsoft (United States)US23 papers
- Carnegie Mellon UniversityUS20 papers
- Massachusetts Institute of TechnologyUS18 papers
- Google (United States)US16 papers
- Technion – Israel Institute of TechnologyIL16 papers
- University of California, BerkeleyUS16 papers
- Princeton UniversityUS12 papers
- The University of Texas at AustinUS12 papers
- Toyota Technological InstituteJP10 papers
- University of TorontoCA10 papers
- University of WashingtonUS10 papers
27 papers · 1 filter
Uniform Convergence of Interpolators: Gaussian Width, Norm Bounds, and Benign Overfitting
Frederic Koehler, Lijia Zhou, Danica J. Sutherland +1
We consider interpolation learning in high-dimensional linear regression with Gaussian data, and prove a generic uniform convergence guarantee on the generalization error of interp…
Does Invariant Risk Minimization Capture Invariance?
Pritish Kamath, Akilesh Tangella, Danica J. Sutherland +1
We show that the Invariant Risk Minimization (IRM) formulation of Arjovsky et al. (2019) can fail to capture "natural" invariances, at least when used in its practical "linear" for…
Predictive Value Generalization Bounds
Keshav Vemuri, Nathan Srebro
In this paper, we study a bi-criterion framework for assessing scoring functions in the context of binary classification. The positive and negative predictive values (ppv and npv,…
On Uniform Convergence and Low-Norm Interpolation Learning
Lijia Zhou, Danica J. Sutherland, Nathan Srebro
We consider an underdetermined noisy linear regression model where the minimum-norm interpolating predictor is known to be consistent, and ask: can uniform convergence in a norm ba…
Learning deep kernels for exponential family densities
Li Wenliang, Danica J. Sutherland, Heiko Strathmann +1
The kernel exponential family is a rich class of distributions, which can be fit efficiently and with statistical guarantees by score matching. Being required to choose a priori a…
Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network
Risi Kondor, Zhen Lin, Shubhendu Trivedi
Recent work by Cohen \emph{et al.} has achieved state-of-the-art results for learning spherical images in a rotation invariant way by using ideas from group representation theory a…