paper-with-me

Papers

Adversarial Classification via Distributional Robustness with Wasserstein Ambiguity

2020-05-28 · Nam Ho-Nguyen, Stephen J. Wright

We study a model for adversarial classification based on distributionally robust chance constraints. We show that under Wasserstein ambiguity, the model aims to minimize the conditional value-at-risk of the distance to misclassification, and we explore links to adversarial classification models proposed earlier and to maximum-margin classifiers. We also provide a reformulation of the distributionally robust model for linear classification, and show it is equivalent to minimizing a regularized ramp loss objective. Numerical experiments show that, despite the nonconvexity of this formulation, standard descent methods appear to converge to the global minimizer for this problem. Inspired by this observation, we show that, for a certain class of distributions, the only stationary point of the regularized ramp loss minimization problem is the global minimizer.

📄 PDF Abstract BibTeX arXiv:2005.13815

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Balls

2024-07-18 · Aras Selvi, Eleonora Kreacic, Mohsen Ghassemi, Vamsi Potluru 외

Adversarially robust optimization (ARO) has emerged as the *de facto* standard for training models that hedge against adversarial attacks in the test stage. While these models are robust against adversarial attacks, they…

regression

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

2023-09-21 · NeurIPS 2023 11

Markov decision processes (MDPs) often suffer from the sensitivity issue under model ambiguity. In recent years, robust MDPs have emerged as an effective framework to overcome this challenge. Distributionally robust MDPs…

On the Generalization of Wasserstein Robust Federated Learning

2022-06-03 · Tung-Anh Nguyen, Tuan Dung Nguyen, Long Tan Le, Canh T. Dinh 외

In federated learning, participating clients typically possess non-i.i.d. data, posing a significant challenge to generalization to unseen distributions. To address this, we propose a Wasserstein distributionally robust …

Domain AdaptationFederated Learning

A Unified Wasserstein Distributional Robustness Framework for Adversarial Training

2022-02-27 · ICLR 2022 4 · Tuan Anh Bui, Trung Le, Quan Tran, He Zhao 외

It is well-known that deep neural networks (DNNs) are susceptible to adversarial attacks, exposing a severe fragility of deep learning systems. As the result, adversarial training (AT) method, by incorporating adversaria…

DR-PETS: Learning-Based Control With Planning in Adversarial Environments

2025-03-26 · Hozefa Jesawada, Antonio Acernese, Giovanni Russo, Carmen Del Vecchio

Ensuring robustness against epistemic, possibly adversarial, perturbations is essential for reliable real-world decision-making. While the Probabilistic Ensembles with Trajectory Sampling (PETS) algorithm inherently hand…

Decision Making