中文
相关论文

相关论文: Natural Geometry of Robust Data Attribution: From …

200 篇论文

Wasserstein distributionally robust optimization (WDRO) strengthens statistical learning under model uncertainty by minimizing the local worst-case risk within a prescribed ambiguity set. Although WDRO has been extensively studied in…

机器学习 · 统计学 2025-11-12 Changyu Liu , Yuling Jiao , Junhui Wang , Jian Huang

Graphs are playing a crucial role in different fields since they are powerful tools to unveil intrinsic relationships among signals. In many scenarios, an accurate graph structure representing signals is not available at all and that…

机器学习 · 计算机科学 2021-05-14 Xiang Zhang , Yinfei Xu , Qinghe Liu , Zhicheng Liu , Jian Lu , Qiao Wang

In this work, we propose Wasserstein distributionally robust shallow convex neural networks (WaDiRo-SCNNs) to provide reliable nonlinear predictions when subject to adverse and corrupted datasets. Our approach is based on the reformulation…

机器学习 · 计算机科学 2025-08-22 Julien Pallage , Antoine Lesage-Landry

Certified robustness in machine learning has primarily focused on adversarial perturbations of the input with a fixed attack budget for each point in the data distribution. In this work, we present provable robustness guarantees on the…

机器学习 · 计算机科学 2023-07-18 Aounon Kumar , Alexander Levine , Tom Goldstein , Soheil Feizi

Wasserstein distributionally robust optimization (WDRO) provides a framework for adversarial robustness, yet existing methods based on global Lipschitz continuity or strong duality often yield loose upper bounds or require prohibitive…

机器学习 · 计算机科学 2026-02-04 Bach C. Le , Tung V. Dao , Binh T. Nguyen , Hong T. M. Chu

We propose REpresentation-Aware Distributionally Robust Estimation (READ), a novel framework for Wasserstein distributionally robust learning that accounts for predictive representations when guarding against distributional shifts. Unlike…

统计方法学 · 统计学 2025-09-12 Zitao Wang , Nian Si , Molei Liu

Machine learning image classifiers are susceptible to adversarial and corruption perturbations. Adding imperceptible noise to images can lead to severe misclassifications of the machine learning model. Using $L_p$-norms for measuring the…

机器学习 · 计算机科学 2021-10-14 Tobias Wegel , Felix Assion , David Mickisch , Florens Greßner

Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set. Current certifications typically rely either on global Lipschitz bounds, which are often conservative, or on local gradient…

最优化与控制 · 数学 2026-04-09 Hong T. M. Chu

In many real-world applications, ensuring the robustness and stability of deep neural networks (DNNs) is crucial, particularly for image classification tasks that encounter various input perturbations. While data augmentation techniques…

机器学习 · 统计学 2025-06-26 Jiaming Hu , Debarghya Mukherjee , Ioannis Ch. Paschalidis

This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks based upon non-Euclidean contraction theory. The basic idea is to cast the robustness analysis of a neural…

机器学习 · 计算机科学 2022-08-09 Saber Jafarpour , Alexander Davydov , Matthew Abate , Francesco Bullo , Samuel Coogan

This monograph develops a comprehensive statistical learning framework that is robust to (distributional) perturbations in the data using Distributionally Robust Optimization (DRO) under the Wasserstein metric. Beginning with fundamental…

机器学习 · 统计学 2021-08-23 Ruidi Chen , Ioannis Ch. Paschalidis

As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity to a strict operational requirement. Our…

机器学习 · 统计学 2026-04-27 Younes Essafouri , Laure Raynaud , Luciano Drozda , Laurent Risser

We present a Distributionally Robust Optimization (DRO) approach to estimate a robustified regression plane in a linear regression setting, when the observed samples are potentially contaminated with adversarially corrupted outliers. Our…

机器学习 · 统计学 2018-05-14 Ruidi Chen , Ioannis Ch. Paschalidis

We consider the rate-distortion function for lossy source compression, as well as the channel capacity for error correction, through the lens of distributional robustness. We assume that the distribution of the source or of the additive…

信息论 · 计算机科学 2024-05-14 Vikrant Malik , Taylan Kargin , Victoria Kostina , Babak Hassibi

Distributionally Robust Optimization (DRO) provides a framework for decision-making under distributional uncertainty, yet its effectiveness can be compromised by outliers in the training data. This paper introduces a principled approach to…

机器学习 · 计算机科学 2025-11-04 Shuyao Li , Ilias Diakonikolas , Jelena Diakonikolas

We propose a distributionally robust logistic regression model with an unfairness penalty that prevents discrimination with respect to sensitive attributes such as gender or ethnicity. This model is equivalent to a tractable convex…

机器学习 · 计算机科学 2020-07-21 Bahar Taskesen , Viet Anh Nguyen , Daniel Kuhn , Jose Blanchet

We develop a novel computationally efficient and general framework for robust hypothesis testing. The new framework features a new way to construct uncertainty sets under the null and the alternative distributions, which are sets centered…

机器学习 · 统计学 2018-05-29 Rui Gao , Liyan Xie , Yao Xie , Huan Xu

Learning to predict multi-label outputs is challenging, but in many problems there is a natural metric on the outputs that can be used to improve predictions. In this paper we develop a loss function for multi-label learning, based on the…

机器学习 · 计算机科学 2015-12-31 Charlie Frogner , Chiyuan Zhang , Hossein Mobahi , Mauricio Araya-Polo , Tomaso Poggio

As the complexity of modern control systems increases, it becomes challenging to derive an accurate model of the uncertainty that affects their dynamics. Wasserstein Distributionally Robust Optimization (DRO) provides a powerful framework…

系统与控制 · 电气工程与系统科学 2025-09-09 Riccardo Cescon , Andrea Martin , Giancarlo Ferrari-Trecate

We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability metrics, such as the…

机器学习 · 计算机科学 2022-02-22 Jia-Jie Zhu , Christina Kouridi , Yassine Nemmour , Bernhard Schölkopf
‹ 上一页 1 2 3 10 下一页 ›