中文
相关论文

相关论文: Comparing Mixture, Box, and Wasserstein Ambiguity …

200 篇论文

We present a novel framework for distributionally robust optimization (DRO), called cost-aware DRO (CADRO). The key idea of CADRO is to exploit the cost structure in the design of the ambiguity set to reduce conservatism. Particularly, the…

最优化与控制 · 数学 2023-05-17 Mathijs Schuurmans , Panagiotis Patrinos

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 study a variety of Wasserstein distributionally robust optimization (WDRO) problems where the distributions in the ambiguity set are chosen by constraining their Wasserstein discrepancies to the empirical distribution. Using the notion…

最优化与控制 · 数学 2024-02-07 Hong T. M. Chu , Meixia Lin , Kim-Chuan Toh

In recent years, two prominent paradigms have shaped distributionally robust optimization (DRO), modeling distributional ambiguity through $\phi$-divergences and Wasserstein distances, respectively. While the former focuses on ambiguity in…

最优化与控制 · 数学 2025-12-22 Jose Blanchet , Daniel Kuhn , Jiajin Li , Bahar Taskesen

Distributionally Robust Optimization (DRO) is a popular framework for decision-making under uncertainty, but its adversarial nature can lead to overly conservative solutions. To address this, we study ex-ante Distributionally Robust Regret…

最优化与控制 · 数学 2025-04-22 Lukas-Benedikt Fiechtner , Jose Blanchet

Empirical risk minimization (ERM) and distributionally robust optimization (DRO) are popular approaches for solving stochastic optimization problems that appear in operations management and machine learning. Existing generalization error…

最优化与控制 · 数学 2023-09-26 Garud Iyengar , Henry Lam , Tianyu Wang

We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers. The DRO framework uses a probabilistic ambiguity set defined as a ball of…

计算机视觉与模式识别 · 计算机科学 2023-03-28 Ruidi Chen , Boran Hao , Ioannis Ch. Paschalidis

We develop a Distributionally Robust Optimization (DRO) formulation for Multiclass Logistic Regression (MLR), which could tolerate data contaminated by outliers. The DRO framework uses a probabilistic ambiguity set defined as a ball of…

机器学习 · 统计学 2023-03-28 Ruidi Chen , Boran Hao , Ioannis Paschalidis

Distributionally robust optimization (DRO)-based robust adaptive beamforming (RAB) enables enhanced robustness against model uncertainties, such as steering vector mismatches and interference-plus-noise covariance matrix estimation errors.…

信号处理 · 电气工程与系统科学 2025-06-03 Kiarash Hassas Irani , Sergiy A. Vorobyov , Yongwei Huang

This paper studies Distributionally Robust Optimization (DRO), a fundamental framework for enhancing the robustness and generalization of statistical learning and optimization. An effective ambiguity set for DRO must involve distributions…

机器学习 · 计算机科学 2025-10-28 Jiaqi Wen , Jianyi Yang

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

Distributionally robust optimization (DRO) studies decision problems under uncertainty where the probability distribution governing the uncertain problem parameters is itself uncertain. A key component of any DRO model is its ambiguity set,…

最优化与控制 · 数学 2025-05-28 Daniel Kuhn , Soroosh Shafiee , Wolfram Wiesemann

In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based safety filtering framework that switches between a high-performance nominal policy and a…

机器人学 · 计算机科学 2026-05-20 Daniel M. Cherenson , Haejoon Lee , Taekyung Kim , Dimitra Panagou

Distributionally robust optimization (DRO) is an effective approach for data-driven decision-making in the presence of uncertainty. Geometric uncertainty due to sampling or localized perturbations of data points is captured by Wasserstein…

机器学习 · 统计学 2023-11-10 Sloan Nietert , Ziv Goldfeld , Soroosh Shafiee

Distributionally robust optimization (DRO) incorporates robustness against uncertainty in the specification of probabilistic models. This paper focuses on mitigating the curse of dimensionality in data-driven DRO problems with optimal…

最优化与控制 · 数学 2023-11-01 Lotfi M. Chaouach , Tom Oomen , Dimitris Boskos

Off-policy evaluation and learning are concerned with assessing a given policy and learning an optimal policy from offline data without direct interaction with the environment. Often, the environment in which the data are collected differs…

机器学习 · 计算机科学 2024-01-18 Yi Shen , Pan Xu , Michael M. Zavlanos

Wasserstein distributionally robust optimization (DRO) aims to find robust and generalizable solutions by hedging against data perturbations in Wasserstein distance. Despite its recent empirical success in operations research and machine…

机器学习 · 计算机科学 2022-05-03 Rui Gao

Distributionally Robust Optimisation (DRO) protects risk-averse decision-makers by considering the worst-case risk within an ambiguity set of distributions based on the empirical distribution or a model. To further guard against finite,…

机器学习 · 统计学 2025-05-07 Charita Dellaporta , Patrick O'Hara , Theodoros Damoulas

Distributionally Robust Optimization (DRO) has enabled to prove the equivalence between robustness and regularization in classification and regression, thus providing an analytical reason why regularization generalizes well in statistical…

最优化与控制 · 数学 2020-07-15 Esther Derman , Shie Mannor

Wasserstein distributionally robust optimization (\textsf{WDRO}) is a popular model to enhance the robustness of machine learning with ambiguous data. However, the complexity of \textsf{WDRO} can be prohibitive in practice since solving its…

机器学习 · 计算机科学 2023-05-10 Ruomin Huang , Jiawei Huang , Wenjie Liu , Hu Ding