# Uniform concentration and symmetrization for weak interactions

arXiv: https://arxiv.org/abs/1902.01911 · HTML: https://mlsanity.com/paper/1902.01911/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2019.

## Built on by (most cited first, 4 of 4)

- [On the Role of Neural Collapse in Transfer Learning](https://mlsanity.com/paper/2112.15121/) (2021)
- [Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers](https://mlsanity.com/paper/2212.12532/) (2022)
- [One-shot Conditional Sampling: MMD meets Nearest Neighbors](https://mlsanity.com/paper/2509.25507/) (2025)
- [Kernel Selection is Model Selection: A Unified Complexity-Penalized Approach for MMD Two-Sample Tests](https://mlsanity.com/paper/2605.06883/) (2026)

## Abstract (arXiv)

The method to derive uniform bounds with Gaussian and Rademacher complexities is extended to the case where the sample average is replaced by a nonlinear statistic. Tight bounds are obtained for U-statistics, smoothened L-statistics and error functionals of l2-regularized algorithms.