Cover Image

Lower Difficulty and Better Robustness: A Bregman Divergence Perspective for Adversarial Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zihui, Gao, Haichang, Zhou, Bingqian, Guo, Xiaoyan, Zhang, Shudong
Format:	Preprint
Published:	2022
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor
by: Wu, Zihui, et al.
Published: (2025)

Rethinking Bregman Divergences in Kronecker-Factored Optimizers
by: Liu, Bing, et al.
Published: (2026)

Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
by: Xing, Yue, et al.
Published: (2024)

A Generalized Bias-Variance Decomposition for Bregman Divergences
by: Pfau, David
Published: (2025)

Online Nonconvex Bilevel Optimization with Bregman Divergences
by: Bohne, Jason, et al.
Published: (2024)

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
by: Palumbo, Nils, et al.
Published: (2023)

Geometric Convergence Analysis of Variational Inference via Bregman Divergences
by: Bohara, Sushil, et al.
Published: (2025)

Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM Reasoning
by: Yuan, Rui, et al.
Published: (2026)

Revisiting the Relationship between Adversarial and Clean Training: Why Clean Training Can Make Adversarial Training Better
by: Zhou, MingWei, et al.
Published: (2025)

Optimal Transport Regularized Divergences: Application to Adversarial Robustness
by: Birrell, Jeremiah, et al.
Published: (2023)

On the KL-Divergence-based Robust Satisficing Model
by: Yan, Haojie, et al.
Published: (2024)

Direct Debiased Machine Learning via Bregman Divergence Minimization
by: Kato, Masahiro
Published: (2025)

Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
by: Rizwan, Hammad, et al.
Published: (2024)

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training
by: Cao, Chuxue, et al.
Published: (2026)

Ignition Phase : Standard Training for Fast Adversarial Robustness
by: Yu-Hang, Wang, et al.
Published: (2025)

Robust Sublinear Convergence Rates for Iterative Bregman Projections
by: Peyré, Gabriel
Published: (2026)

A Unified Framework for Debiased Machine Learning: Riesz Representer Fitting under Bregman Divergence
by: Kato, Masahiro
Published: (2026)

GlitchMiner: Mining Glitch Tokens in Large Language Models via Gradient-based Discrete Optimization
by: Wu, Zihui, et al.
Published: (2024)

Symmetrizing Bregman Divergence on the Cone of Positive Definite Matrices: Which Mean to Use and Why
by: Sial, Tushar, et al.
Published: (2026)

Robustness Feature Adapter for Efficient Adversarial Training
by: Wu, Quanwei, et al.
Published: (2025)

A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
by: Zhang, Johnny R., et al.
Published: (2025)

On the Robustness of Adversarial Training Against Uncertainty Attacks
by: Ledda, Emanuele, et al.
Published: (2024)

DRIFT: Divergent Response in Filtered Transformations for Robust Adversarial Defense
by: Guesmi, Amira, et al.
Published: (2025)

Vulnerability-Aware Robust Multimodal Adversarial Training
by: Zhang, Junrui, et al.
Published: (2025)

Explanation-Guided Adversarial Training for Robust and Interpretable Models
by: Chen, Chao, et al.
Published: (2026)

Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectives
by: Liu, Wei, et al.
Published: (2026)

Adversarial Training for Robust Coverage Network under Worst-case Facility Losses
by: Miao, Changhao, et al.
Published: (2026)

Whispers of Data: Unveiling Label Distributions in Federated Learning Through Virtual Client Simulation
by: Ma, Zhixuan, et al.
Published: (2025)

$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
by: Li, Pengyu, et al.
Published: (2026)

Adapting to Evolving Adversaries with Regularized Continual Robust Training
by: Dai, Sihui, et al.
Published: (2025)

Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics
by: Croce, Francesco, et al.
Published: (2025)

Lower Bounds on Adversarial Robustness for Multiclass Classification with General Loss Functions
by: Trillos, Camilo Andrés García, et al.
Published: (2025)

L-MoE: End-to-End Training of a Lightweight Mixture of Low-Rank Adaptation Experts
by: Ji, Shihao, et al.
Published: (2025)

Rethinking the Sampling Criteria in Reinforcement Learning for LLM Reasoning: A Competence-Difficulty Alignment Perspective
by: Kong, Deyang, et al.
Published: (2025)

Symplectic Bregman divergences
by: Nielsen, Frank
Published: (2024)

Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective
by: Liu, Yu-An, et al.
Published: (2024)

Feature Statistics with Uncertainty Help Adversarial Robustness
by: Wang, Ran, et al.
Published: (2025)

An Optimal Transport Approach for Computing Adversarial Training Lower Bounds in Multiclass Classification
by: Trillos, Nicolas Garcia, et al.
Published: (2024)

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses
by: Yichao, Wu, et al.
Published: (2025)

On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars
by: Tao, Chun, et al.
Published: (2021)