Research map / Probabilistic and scientific modeling / Variational and generative sampling
Isometric Regularization for Manifolds of Functional Data
Read the paperCheck your idea against 108,967 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 isometric regularization for latent spaces of implicit neural representation (INR) decoders so that the learned manifold of functional data preserves distances.
Problem
Modeling the distribution of functional data represented by implicit neural representations, where a shared network maps latent vectors to functions, and the latent manifold may be poorly structured.
Approach
Applies an isometry-based regularizer to the shared INR decoder so that the latent space respects the geometry of the functional data manifold; described only at high level in the abstract.
Closest papers by meaning
- Regularized Autoencoders for Isometric Representation Learning (ICLR 2022 · similarity 0.89)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 2025 · similarity 0.88)
- Latent Functional Maps: a spectral framework for representation alignment (NeurIPS 2024 · similarity 0.87)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.86)
- Dual Manifold Regularization Steered Robust Representation Learning for Point Cloud Analysis (AAAI 2025 · similarity 0.86)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · 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.