Research map / Learning theory and algorithms / Optimal transport
Tree-Sliced Entropy Partial Transport
Viet-Hoang Tran, Thanh Tran, Thanh Chu, Tam Le, Tan Minh Nguyen
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 a tree-sliced entropic partial transport method for comparing unbalanced distributions in machine learning, building on partial optimal transport.
Problem
Classical optimal transport requires equal total mass between source and target distributions, which limits its use on imbalanced data, noisy data, outliers, and structural inconsistencies.
Approach
Combines tree-sliced transport with entropic partial transport so that partial, mass-relaxed comparisons of distributions can be computed efficiently; the abstract only indicates this extends partial transport to a sliced, tree-based setting.
Experimental setup
Builds on: partial optimal transport tree-sliced optimal transport
Closest papers by meaning
- Tree-Sliced Wasserstein Distance: A Geometric Perspective (ICML 2025 · similarity 0.91)
- Distance-Based Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.91)
- Expected Sliced Transport Plans (ICLR 2025 · similarity 0.90)
- Differentiable Generalized Sliced Wasserstein Plans (NeurIPS 2025 · similarity 0.89)
- Learning Ultrametric Trees for Optimal Transport Regression (AAAI 2024 · similarity 0.89)
- Spherical Tree-Sliced Wasserstein Distance (ICLR 2025 · similarity 0.89)
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.
