Research map / Learning theory and algorithms / Optimal transport
Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport
Pankaj K Agarwal, Sharath Raghvendra, Pouyan Shirzadian, Keegan Yao
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.
Studies robust and partial variants of semi-discrete optimal transport in R^d, giving efficient algorithms for the alpha-partial transport and lambda-TV-robust formulations.
Problem
Optimal transport is sensitive to noise, so robust variants (partial transport with mass alpha, and TV-regularized robust OT) are needed; the paper targets efficient computation for these in the semi-discrete setting in R^d.
Approach
Studies two robust semi-discrete OT formulations: alpha-optimal partial transport (transport only a mass alpha) and lambda-robust OT (TV-distance regularization), and develops efficient algorithms for them. Full method details are unavailable from the abstract provided.
Closest papers by meaning
- On Robust Optimal Transport: Computational Complexity and Barycenter Computation (NeurIPS 2021 · similarity 0.92)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.89)
- Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate (NeurIPS 2025 · similarity 0.89)
- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport (NeurIPS 2025 · similarity 0.86)
- A Truncated Newton Method for Optimal Transport (ICLR 2025 · similarity 0.86)
- Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport (NeurIPS 2026 · similarity 0.86)
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.
