paper-with-me

Papers

Stability and Generalization of Adversarial Diffusion Training

2025-09-23 · Hesam Hosseini, Ying Cao, Ali H. Sayed arxiv

Algorithmic stability is an established tool for analyzing generalization. While adversarial training enhances model robustness, it often suffers from robust overfitting and an enlarged generalization gap. Although recent work has established the convergence of adversarial training in decentralized networks, its generalization properties remain unexplored. This work presents a stability-based generalization analysis of adversarial training under the diffusion strategy for convex losses. We derive a bound showing that the generalization error grows with both the adversarial perturbation strength and the number of training steps, a finding consistent with single-agent case but novel for decentralized settings. Numerical experiments on logistic regression validate these theoretical predictions.

📄 PDF Abstract BibTeX arXiv:2509.19234

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Data-Dependent Stability Analysis of Adversarial Training

2024-01-06 · Yihan Wang, Shuang Liu, Xiao-Shan Gao

Stability analysis is an essential aspect of studying the generalization ability of deep learning, as it involves deriving generalization bounds for stochastic gradient descent-based training algorithms. Adversarial trai…

Data PoisoningGeneralization Bounds

Stability and Generalization in Free Adversarial Training

2024-04-13 · Xiwei Cheng, Kexin Fu, Farzan Farnia

While adversarial training methods have significantly improved the robustness of deep neural networks against norm-bounded adversarial perturbations, the generalization gap between their performance on training and test …

Generalization Bounds

Phased One-Step Adversarial Equilibrium for Video Diffusion Models

2025-08-28 · Jiaxiang Cheng, Bing Ma, Xuhua Ren, Hongyi Henry Jin 외 arxiv

Video diffusion generation suffers from critical sampling efficiency bottlenecks, particularly for large-scale models and long contexts. Existing video acceleration methods, adapted from image-based techniques, lack a si…

Video Generation

On the Algorithmic Stability of Adversarial Training

2021-12-01 · NeurIPS 2021 12 · Yue Xing, Qifan Song, Guang Cheng

The adversarial training is a popular tool to remedy the vulnerability of deep learning models against adversarial attacks, and there is rich theoretical literature on the training loss of adversarial training algorithms…

Stability Analysis and Generalization Bounds of Adversarial Training

2022-10-03 · Jiancong Xiao, Yanbo Fan, Ruoyu Sun, Jue Wang 외

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon is called robust overfitting, and it ca…

Generalization Bounds