Linear unit-tests for invariance discovery

Causal Discovery & Causality Workshop at NeurIPS

Abstract

There is an increasing interest in algorithms to learn invariant correlations across training environments. A big share of the current proposals find theoretical support in the causality literature but, how useful are they in practice? The purpose of this note is to propose six linear low-dimensional problems—“unit tests”—to evaluate out-of-distribution generalization algorithms. Following initial experiments, none of three recently proposed alternatives pass these tests. By providing the code to automatically replicate all the results in this manuscript (https://github. com/anonymous), we hope that the development of unit tests becomes a standard stepping stone for researchers in out-of-distribution generalization.

Latest Publications

Log-structured Protocols in Delos

Mahesh Balakrishnan, Mihir Dharamshi, David Geraghty, Santosh Ghosh, Filip Gruszczynski, Jun Li, Jingming Liu, Suyog Mapara, Rajeev Nagar, Ivailo Nedelchev, Francois Richard, Chen Shen, Yee Jiun Song, Rounak Tibrewal, Vidhya Venkat, Ahmed Yossef, Ali Zaveri

SOSP