Skip to content

Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning

Sep 2026 · 0 citations · 79 references
Computer Science Mathematics

TL;DR

A penalized DRO formulation in which the adversary may choose any distribution but incurs a Wasserstein penalty for deviating from the empirical distribution is studied, showing that the adversary's problem can be reformulated as an optimization problem over transport maps that push empirical samples to adversarial ones, and it is proved that optimal maps are cyclically monotone.

Abstract

Distributionally robust optimization (DRO) provides a principled framework for learning under distribution shift, but its practical use is hindered by the difficulty of evaluating worst-case risks for nonconvex loss functions. We study a penalized DRO formulation in which the adversary may choose any distribution but incurs a Wasserstein penalty for deviating from the empirical distribution. We show that the adversary's problem can be reformulated as an optimization problem over transport maps that push empirical samples to adversarial ones, and we prove that optimal maps are cyclically monotone. We also show that standard adversarial training---based on per-sample local optimization---violates cyclical monotonicity and wastes transport costs unless the adversary is severely restricted. We propose two remedies. First, we introduce multi-start particle ascent, which alternates parallel gradient ascent with reassignment to enforce cyclical monotonicity across samples. Second, we parameterize adversarial maps as gradients of input-convex neural networks, which guarantees cyclical monotonicity by construction. Experiments on robust regression, image classification, and robust control show that our methods consistently outperform standard adversarial training and state-of-the-art baselines, achieving improved robustness and better generalization under distribution shift.

View source

Similar papers

#machine learning Preprint Sep 2026

Distributionally robust linear regression through the lens of adversarial training

Distributionally robust optimization (DRO) studies parameter estimation under uncertainty in the underlying probability distribution and has emerged as a principled framework for analyzing robustness and generalization. In particular, Wasserstein DRO, with distributional uncertainty induced by the Wasserstein distance,...

Elis Stefansson, David Vävinggren, Antônio H. Ribeiro · 0 citations
Open access Sep 2026

DWAT: Density-Weighted Adversarial Training for Robustness Beyond the Training Perturbation Budget

Density-Weighted Adversarial Training is presented, a plug-in framework that spreads training over a set of sampled ϵ-balls and reweights each candidate adversarial example by a Gaussian density of its distance from the benign sample, and it is proved that the population objective upper-bounds the worst-case adversaria...

Jie-Ying Huang, Rui-Ming Zhu, Jia Xu et al. · 0 citations
#machine learning Preprint Sep 2026

Robust Policy Optimization via Adversarial Importance Sampling

This work introduces Adversarial Importance Sampling (Advis), a method that uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns and introduces advrl, a modular PyTorch library that provides clean, single-file implementations of existing robustness met...

Amine Andam, Jamal Bentahar, M. Hedabou · 0 citations
Preprint Aug 2026

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

This work proposes BMAT (Bilevel-Minimax Adversarial Transfer), an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization.

Yao-Hua Liu, Yi-Fan Guo, Jia-Xin Gao · 0 citations
Conference Open access Sep 2026

Diverge to Converge: Mutual Heterogeneous Learning for Robust Pruning

Mutual Heterogeneous Learning (MHL) is proposed, a framework enabling robust pruning via single-model inference that significantly outperforms single-model baselines in both adversarial robustness and corruption robustness, while maintaining competitive clean accuracy.

Jin-Hui Yu, Zikai Zhang, Khaled A. Harras et al. · 0 citations
#machine learning Preprint Sep 2026

Statistical Inference for Adversarial Training: Central Limit Theorems via Optimal Transport

The purpose of this paper is to rigorously quantify the statistical and learning-theoretic properties of adversarial training models for classification. Equivalently, we establish the statistical properties of empirical optimal partial transport. Precisely, first we provide two types of central limit theorems (CLT): CL...

Kim Jakwang, Kwon Dohyun · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.