Comfort Zone: A Vicinal Distribution for Regression Problems

Roee Weiss Lifshitz, Omri Azencot

Keywords: Deep Learning Regularization, Data Augmentation, Regression Learning

Abstract: Domain-dependent data augmentation methods generate artificial samples using transformations suited for the underlying data domain, for example rotations on images and time warping on time series data. However, domain-independent approaches, e.g. mixup, are applicable to various data modalities, and as such they are general and versatile. While mixup-based techniques are used extensively in classification problems, their effect on regression tasks is somewhat less explored. To bridge this gap, we study the problem of domain-independent augmentation for regression, and we introduce comfort-zone: a new data-driven, domain-independent data augmentation method. Essentially, our approach samples new examples from the tangent planes of the train distribution. Augmenting data in this way aligns with the network tendency towards capturing the dominant features of its input signals. Evaluating comfort-zone on regression and time series forecasting benchmarks, we show that it improves the generalization of several neural architectures. We also find that mixup and noise injection are less effective in comparison to comfort-zone.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning