Research map / Learning theory and algorithms / Optimal transport
Averaging Spatio-temporal Signals using Optimal Transport and Soft Alignment
Hicham Janati, Marco Cuturi, Alexandre Gramfort
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 |
|---|---|---|---|
| use debiased UOT barycenter instead of the biased UOT barycenter (ablation) | unbalanced OT barycenter · Gaussian barycenters with 3 values of epsilon | sensitivity to entropic regularization / sharpness | Improved |
| add temporal soft-DTW alignment (STA) to the per-time-step OT barycenter (ablation) | OT barycenter · DS117 EEG/MEG brain imaging (6 subjects) | activation focus at FFA and timing of first evoked response | Improved |
| use STA barycenter instead of Euclidean mean | brain activity averaging · DS117 EEG/MEG brain imaging (6 subjects) | l2 norm across space, evoked responses visibility | Improved |
| use OT-based loss instead of l2 for neighbor selection and barycenter | barycenter forecasting · handwritten letters forecasting | neighbor class identification | Improved |
| add soft-DTW temporal alignment to OT (STA vs OT alone) (ablation) | barycenter forecasting · handwritten letters forecasting | prediction accuracy of remaining time points | Improved |
| use STA loss instead of l2 and EMD-only losses | barycenter forecasting · handwritten letters (l2 and EMD scores) | l2 and EMD prediction error | Improved |
Closest papers by meaning
- Manifold Interpolating Optimal-Transport Flows for Trajectory Inference (NeurIPS 2022 · similarity 0.86)
- Dynamical Wasserstein Barycenters for Time-series Modeling (NeurIPS 2021 · similarity 0.85)
- Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model (NeurIPS 2024 · similarity 0.85)
- Hierarchical Optimal Transport for Multimodal Distribution Alignment (NeurIPS 2019 · similarity 0.85)
- Comparing noisy neural population dynamics using optimal transport distances (ICLR 2025 · similarity 0.85)
- PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation (NeurIPS 2026 · similarity 0.83)
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.
