Research map / Learning theory and algorithms / Optimal transport
Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization
Weiming Liu, Xinting Liao, Jun Dan, Fan Wang, Hua Yu, Junhao Dong, Shunjie Dong, Lianyong Qi, Yew-Soon Ong
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 equivalent transformation mechanism and KKT-multiplier regularization for solving discrete semi-unbalanced optimal transport with KL divergence, avoiding entropy regularization that the authors say yields inaccurate matchings.
Problem
Discrete semi-unbalanced optimal transport (SemiUOT), which matches two probability measures while relaxing one marginal constraint, is typically solved with entropic regularization that can produce inaccurate matching solutions.
Approach
Determines the marginal distribution of SemiUOT with KL divergence via an equivalent transformation mechanism and uses KKT-multiplier regularization in place of entropy regularization, aiming for more accurate matching solutions.
Experimental setup
Builds on: unbalanced optimal transport Sinkhorn algorithm
Closest papers by meaning
- Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm. (ICML 2023 · similarity 0.89)
- Light Unbalanced Optimal Transport (NeurIPS 2024 · similarity 0.88)
- Submodular framework for structured-sparse optimal transport (ICML 2024 · similarity 0.88)
- Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate (NeurIPS 2025 · similarity 0.87)
- Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport (NeurIPS 2025 · similarity 0.87)
- A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem (NeurIPS 2024 · similarity 0.87)
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.
