We consider a minimax problem motivated by distributionally robust optimization (DRO) when the worst-case distribution is continuous, leading to significant computational challenges due to the infinite-dimensional nature of the optimization problem. Recent research has explored learning the worst-case ...
In this paper, we propose a novel Stable Adversarial Learning (SAL) algorithm that leverages heterogeneous data sources to construct a more practical uncertainty set and conduct differentiated robustness optimization, where covariates are differentiated according to the stability of their correlations with ...
In this paper, we propose a new task-level Distributionally Robust Optimization (tDRO) algorithm for LLM-DR fine-tuning, targeted at improving the universal domain generalization ability by end-to-end reweighting the data distribution of each task. The tDRO parameterizes the domain weights and ...
Combining the merits of robust optimation and SO, DRO was further proposed. Similar to the RO method, the DRO method also has a two-stage structure, which can be solved by C&CG algorithm. The confidence set oriented to the worst probability distribution of DRO method is based on historical...
Basics of distributionally robust optimization In this section, we first introduce the concept of ambiguity set and revisit some formulations widely adopted in literature. After that, a tractable deterministic reformulation of the single-stage problem is derived. All materials in this section come from...
We study decision dependent distributionally robust optimization models, where the ambiguity sets of probability distributions can depend on the decision v
Distributionally robust optimization Mean-CVaR model Cardinality constraint Modified bilevel cutting-plane algorithm Mathematics Subject Classification 91B70 91G10 60E99 Access this article Subscribe and save Springer+ Basic €32.70 /Month Get 10 units per month ...
Uncertain Scheduling of the Power System Based on Wasserstein Distributionally Robust Optimization and Improved Differential Evolution Algorithm... M Lin,LI Bin,C Cecati - 应用数学和力学(英文版) 被引量: 0发表: 2025年 Residuals-Based Contextual Distributionally Robust Optimization with Decision-Dependent ...
By leveraging the strong connection between distributionally robust optimization and regularization, we establish a linear convergence rate to a performatively stable point and provide a suboptimality performance guarantee for the proposed algorithm. Finally, we examine the performance of our proposed model...
The requirement for LFD to be continuous is so that the algorithm can be scalable to problems with larger sample sizes and achieve better generalization capability for the induced robust algorithms. To tackle the computationally challenging infinitely dimensional optimization problem, we leverage flow-...