# Does Data Augmentation Lead to Positive Margin?

arXiv: https://arxiv.org/abs/1905.03177 · HTML: https://mlsanity.com/paper/1905.03177/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2019.

## Built on by (most cited first, 18 of 18)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization](https://mlsanity.com/paper/2210.06441/) (2022)
- [The Trickle-down Impact of Reward (In-)consistency on RLHF](https://mlsanity.com/paper/2309.16155/) (2023)
- [Sample Efficiency of Data Augmentation Consistency Regularization](https://mlsanity.com/paper/2202.12230/) (2022)
- [The Benefits of Mixup for Feature Learning](https://mlsanity.com/paper/2303.08433/) (2023)
- [Data Augmentation as Feature Manipulation](https://mlsanity.com/paper/2203.01572/) (2022)
- [Data Augmentation vs. Equivariant Networks: A Theory of Generalization on Dynamics Forecasting](https://mlsanity.com/paper/2206.09450/) (2022)
- [Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup](https://mlsanity.com/paper/2210.13512/) (2022)
- [Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation](https://mlsanity.com/paper/2206.01909/) (2022)
- [It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness](https://mlsanity.com/paper/2303.09767/) (2023)
- [Recent Advances in Large Margin Learning](https://mlsanity.com/paper/2103.13598/) (2021)
- [BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classification](https://mlsanity.com/paper/2403.06138/) (2024)
- [Data-Efficient Augmentation for Training Neural Networks](https://mlsanity.com/paper/2210.08363/) (2022)
- [Provable Benefit of Cutout and CutMix for Feature Learning](https://mlsanity.com/paper/2410.23672/) (2024)
- [For Better or For Worse? Learning Minimum Variance Features With Label Augmentation](https://mlsanity.com/paper/2402.06855/) (2024)
- [How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reduction](https://mlsanity.com/paper/2507.11161/) (2025)
- [Unproportional mosaicing](https://mlsanity.com/paper/2303.02081/) (2023)
- [Randomized Dimension Reduction with Statistical Guarantees](https://mlsanity.com/paper/2310.01739/) (2023)

## Abstract (arXiv)

Data augmentation (DA) is commonly used during model training, as it significantly improves test error and model robustness. DA artificially expands the training set by applying random noise, rotations, crops, or even adversarial perturbations to the input data. Although DA is widely used, its capacity to provably improve robustness is not fully understood. In this work, we analyze the robustness that DA begets by quantifying the margin that DA enforces on empirical risk minimizers. We first focus on linear separators, and then a class of nonlinear models whose labeling is constant within small convex hulls of data points. We present lower bounds on the number of augmented data points required for non-zero margin, and show that commonly used DA techniques may only introduce significant margin after adding exponentially many points to the data set.