Research map / Optimization / Nonconvex and smooth optimization
Robust Optimization over Multiple Domains
Qi Qian, Shenghuo Zhu, Jiasheng Tang, Rong Jin, Baigui Sun, Hao Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Learn model and adversarial domain weights jointly instead of using even weights | Mixture_Opt versus Mixture_Even · Pets categorization | worst-case test accuracy (%): 88.50 -> 89.35 | Improved |
| Learn model and adversarial domain weights jointly instead of using even weights | Mixture_Opt versus Mixture_Even · Digits recognition | worst-case test accuracy (%): 91.33 -> 92.14 | Improved |
| Train one model on multiple domains rather than an individual domain | Pets categorization · Pets categorization | worst-case test accuracy (%): 80.44 -> 89.35 | Improved |
| Train one model on multiple domains rather than an individual domain | Digits recognition · Digits recognition | worst-case test accuracy (%): 68.25 -> 92.14 | Improved |
| Use a strongly concave L2 regularizer instead of no distribution regularizer (ablation) | Robust optimization over multiple domains · Noisy ImageNet pets domains | worst-case performance | Improved |
| Constrain adversarial weights toward a prior using the regularization strength (ablation) | Mixture_Opt · Pets categorization | inter-domain loss discrepancy | Improved |
| Use the OT distribution regularizer instead of the L2 regularizer (ablation) | Mixture_Opt · Pets categorization | inter-domain loss discrepancy | Mixed |
| Use the delayed distribution step size 1/(lambda(t+c)) with an appropriate c (ablation) | Regularized robust optimization · Non-convex convergence analysis | adversarial-distribution regret | Improved |
Closest papers by meaning
- Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization (NeurIPS 2022 · similarity 0.84)
- CAP: Robust Point Cloud Classification via Semantic and Structural Modeling (CVPR 2023 · similarity 0.84)
- Towards Adversarially Robust Dataset Distillation by Curvature Regularization (AAAI 2025 · similarity 0.83)
- Robust NAS under adversarial training: benchmark, theory, and beyond (ICLR 2024 · similarity 0.83)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.83)
- Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization (NeurIPS 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
