Research map / Probabilistic and scientific modeling / Variational and generative sampling
Local Manifold Identification with Latent Linear Models and OT Flows
Sherman Khoo, Song Liu, Mark Beaumont
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 recovering local data-manifold geometry around a query point by using a pretrained optimal transport flow from reference to data distribution, with latent linear models.
Problem
Identifying the local manifold structure of a dataset around a query point, to reveal hidden signals and remove noise.
Approach
Uses a pretrained OT flow from the reference to the data distribution and analyzes it locally with latent linear models to recover the data manifold geometry in a neighborhood of a query point; abstract is truncated so the full mechanism is not confirmed.
Closest papers by meaning
- Diffusion Models Encode the Intrinsic Dimension of Data Manifolds (ICML 2024 · similarity 0.87)
- Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization (ICML 2025 · similarity 0.87)
- Recovering Manifold Structure Using Ollivier Ricci Curvature (ICLR 2025 · similarity 0.87)
- Categorical Flow Matching on Statistical Manifolds (NeurIPS 2024 · similarity 0.87)
- Learning Distributions on Manifolds with Free-Form Flows (NeurIPS 2024 · similarity 0.86)
- The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction (ICML 2025 · 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.
