Research map / Learning theory and algorithms / Optimal transport
Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport
Jiawei Huang, Minming Li, Hu Ding
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes an adaptive distributionally robust optimization method for classification that builds the uncertainty set using optimal transport, with the set driven by bootstrapped uncertainty estimates.
Problem
Deep learning models degrade under distribution shift, and the effectiveness of distributionally robust optimization depends heavily on how the uncertainty set is designed, which existing methods often do suboptimally.
Approach
Uses optimal transport to define the DRO uncertainty set adaptively, guided by bootstrap-based uncertainty, rather than using a fixed hand-designed set. Only the abstract was available, so finer details are not stated.
Experimental setup
Builds on: distributionally robust optimization
Closest papers by meaning
- Optimal Transport Model Distributional Robustness (NeurIPS 2023 · similarity 0.87)
- Structure-informed Risk Minimization for Robust Ensemble Learning (ICML 2025 · similarity 0.87)
- Distributionally Robust Optimization via Generative Ambiguity Modeling (ICLR 2026 · similarity 0.87)
- Modeling the Second Player in Distributionally Robust Optimization (ICLR 2021 · similarity 0.87)
- Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport (NeurIPS 2024 · similarity 0.86)
- SURE: SUrvey REcipes for building reliable and robust deep networks (CVPR 2024 · similarity 0.85)
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.
