Anchor Data Augmentation as a Generalized Variant of C-Mixup

Authors:

(1) Nora Schneider, Computer Science Department, ETH Zurich, Zurich, Switzerland (nschneide@student.ethz.ch);

(2) Shirin Goshtasbpour, Computer Science Department, ETH Zurich, Zurich, Switzerland and Swiss Data Science Center, Zurich, Switzerland (shirin.goshtasbpour@inf.ethz.ch);

(3) Fernando Perez-Cruz, Computer Science Department, ETH Zurich, Zurich, Switzerland and Swiss Data Science Center, Zurich, Switzerland (fernando.perezcruz@sdsc.ethz.ch).

Table of Links

Abstract and 1 Introduction

2 Background

2.1 Data Augmentation

2.2 Anchor Regression

3 Anchor Data Augmentation

3.1 Comparison to C-Mixup and 3.2 Preserving nonlinear data structure

3.3 Algorithm

4 Experiments and 4.1 Linear synthetic data

4.2 Housing nonlinear regression

4.3 In-distribution Generalization

4.4 Out-of-distribution Robustness

5 Conclusion, Broader Impact, and References

A Additional information for Anchor Data Augmentation

B Experiments

3.1 Comparison to C-Mixup

3.2 Preserving nonlinear data structure

The AR modification Equations 5 and 6 do not preserve the nonlinear relation between the target and predictors,

This paper is available on arxiv under CC0 1.0 DEED license.