Research map / Probabilistic and scientific modeling / Variational and generative sampling
Breaking Curse of Dimensionality for Mutual Information Estimation with Vine Copulas
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 a vine copula-based mutual information estimator whose convergence rate does not depend on data dimensionality.
Problem
Mutual information estimation in high dimensions suffers from the curse of dimensionality for non-parametric density estimators.
Approach
Uses a non-parametric vine copula, whose convergence rate is independent of dimension, to estimate mutual information in an interpretable way.
Closest papers by meaning
- Neural Mutual Information Estimation with Vector Copulas (NeurIPS 2025 · similarity 0.94)
- A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets (NeurIPS 2024 · similarity 0.88)
- Mutual Information Estimation via $f$-Divergence and Data Derangements (NeurIPS 2024 · similarity 0.88)
- Mutual Information Estimation via Normalizing Flows (NeurIPS 2024 · similarity 0.87)
- InfoNet: Neural Estimation of Mutual Information without Test-Time Optimization (ICML 2024 · similarity 0.87)
- FMMI: Flow Matching Mutual Information Estimation (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.