2021-07-01-bao21a.md

title	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers	We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using a classifier trained on one environment to make predictions on examples from another environment, its mistakes are informative as to which correlations are unstable. In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes. Since the oracle interpolation coefficients are not accessible, we use group distributionally robust optimization to minimize the worst-case risk across all such interpolations. We evaluate our method on both text classification and image classification. Empirical results demonstrate that our algorithm is able to learn robust classifiers (outperforms IRM by 23.85% on synthetic environments and 12.41% on natural environments). Our code and data are available at https://github.com/YujiaBao/ Predict-then-Interpolate.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bao21a	0	Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers	640	650	640-650	640	false	Bao, Yujia and Chang, Shiyu and Barzilay, Regina	given family Yujia Bao given family Shiyu Chang given family Regina Barzilay	2021-07-01		Proceedings of the 38th International Conference on Machine Learning	139	inproceedings	date-parts 2021 7 1	http://proceedings.mlr.press/v139/bao21a/bao21a.pdf	label link Supplementary PDF http://proceedings.mlr.press/v139/bao21a/bao21a-supp.pdf