Research map / Optimization / Nonconvex and smooth optimization
Semi-Dual Unbalanced Quadratic Optimal Transport: fast statistical rates and convergent algorithm.
Adrien Vacher, François-Xavier Vialard
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 |
|---|---|---|---|
| Semi-dual formulation (strongly convex potentials) instead of Sinkhorn for unbalanced OT potential estimation | Unbalanced OT potential estimation · 6D synthetic experiment, n=400 samples | squared error ||z_hat - z0||^2 | Improved |
| Increase strong convexity parameter lambda to 2.0 (beyond true 1-strong convexity of z0) (ablation) | Semi-dual model · 6D synthetic experiment | squared error ||z_hat - z0||^2 | Hurt |
| Semi-dual model used in place of Sinkhorn for balanced 2D shape matching | Semi-dual OT (lambda=0.2, L=1) · 2D shape matching | qualitative sharpness of pushforward | Improved |
| Variable metric descent (semi-dual, Bregman-based) vs Frank-Wolfe in balanced 2D experiment | Semi-dual optimization algorithm · Balanced potential recovery (Fig. 2) | convergence speed (iterations) | Improved |
| Exponential convergence for smooth strongly convex potentials (balanced) vs only strongly convex potentials (ablation) | Variable metric descent on semi-dual · Balanced case, Fig. 3 | convergence of log squared L2 gradient error | Improved |
| Unbalanced case instead of balanced case for variable metric descent (ablation) | Semi-dual optimization algorithm · Simple 1D example, Fig. 4 | convergence speed | Hurt |
| Semi-dual with convexity constraint vs SSNB non-convex objective in balanced 2D shape matching | Semi-dual OT vs SSNB · 2D shape matching | W2^2 between pushforward and target | Improved |
Closest papers by meaning
- Minimax Optimal Estimation of Transport-Growth Pairs in Unbalanced Optimal Transport (NeurIPS 2026 · similarity 0.87)
- Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action (NeurIPS 2025 · similarity 0.86)
- Light Unbalanced Optimal Transport (NeurIPS 2024 · similarity 0.85)
- On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods (AAAI 2024 · similarity 0.85)
- Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate (NeurIPS 2025 · similarity 0.85)
- A Provably Convergent and Practical Algorithm for Gromov–Wasserstein Optimal Transport (NeurIPS 2026 · 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.
