activity
20182023
most citedDoes Invariant Risk Minimization Capture Invariance?

23 citations · 30 across the 4 of their papers we have counts for

collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML20222 cited

A Non-Asymptotic Moreau Envelope Theory for High-Dimensional Generalized Linear Models

Lijia Zhou, Frederic Koehler, Pragya Sur +2

We prove a new generalization bound that shows for any class of linear predictors in Gaussian space, the Rademacher complexity of the class and the training error under any continu…

stat.ML20225 cited

Better Supervisory Signals by Observing Learning Paths

Yi Ren, Shangmin Guo, Danica J. Sutherland

Better-supervised models might have better performance. In this paper, we first clarify what makes for good supervision for a classification problem, and then explain two existing…

stat.ML202123 cited

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…

stat.ML2020

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…

stat.ML2020

Learning Deep Kernels for Non-Parametric Two-Sample Tests

Feng Liu, Wenkai Xu, Jie Lu +3

We propose a class of kernel-based two-sample tests, which aim to determine whether two sets of samples are drawn from the same distribution. Our tests are constructed from kernels…

stat.ML2018

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…