paper-with-me

홈 › Papers

A Group-Theoretic Framework for Data Augmentation

2019-07-25 · NeurIPS 2020 12 · Shuxiao Chen, Edgar Dobriban, Jane H Lee

Data augmentation is a widely used trick when training deep neural networks: in addition to the original data, properly transformed data are also added to the training set. However, to the best of our knowledge, a clear mathematical framework to explain the performance benefits of data augmentation is not available. In this paper, we develop such a theoretical framework. We show data augmentation is equivalent to an averaging operation over the orbits of a certain group that keeps the data distribution approximately invariant. We prove that it leads to variance reduction. We study empirical risk minimization, and the examples of exponential families, linear regression, and certain two-layer neural networks. We also discuss how data augmentation could be used in problems with symmetry where other approaches are prevalent, such as in cryo-electron microscopy (cryo-EM).

📄 PDF Abstract BibTeX arXiv:1907.10905

Code (1)

dobriban/data_aug 공식 구현 pytorch

Tasks

Data AugmentationImage Classification

Similar Papers 제목 키워드 기반

The geometry of invariant learning: an information-theoretic analysis of data augmentation and generalization

2026-02-16 · Abdelali Bouyahia, Frédéric LeBlanc, Mario Marchand arxiv

Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its the…

Data Augmentation

Data Augmentation: A Fourier Analysis Perspective

2026-06-23 · Behrooz Tahmasebi, Melanie Weber, Stefanie Jegelka arxiv

Data augmentation is a simple and model-agnostic approach for exploiting known invariances in learning problems. Given a group acting on the input space, one augments the training set with transformed copies of each samp…

Data Augmentation

Model Patching: Closing the Subgroup Performance Gap with Data Augmentation

2020-08-15 · ICLR 2021 1 · Karan Goel, Albert Gu, Yixuan Li, Christopher Ré

Classifiers in machine learning are often brittle when deployed. Particularly concerning are models with inconsistent performance on specific subgroups of a class, e.g., exhibiting disparities in skin cancer classificati…

Cancer ClassificationData AugmentationSkin Cancer Classification

Restrained Generative Adversarial Network against Overfitting in Numeric Data Augmentation

2020-10-26 · Wei Wang, Yimeng Chai, Tao Cui, Chuang Wang 외

In recent studies, Generative Adversarial Network (GAN) is one of the popular schemes to augment the image dataset. However, in our study we find the generator G in the GAN fails to generate numerical data in lower-dimen…

Data AugmentationGenerative Adversarial Network

How Tempering Fixes Data Augmentation in Bayesian Neural Networks

2022-05-27 · Gregor Bachmann, Lorenzo Noci, Thomas Hofmann

While Bayesian neural networks (BNNs) provide a sound and principled alternative to standard neural networks, an artificial sharpening of the posterior usually needs to be applied to reach comparable performance. This is…

Data Augmentation