Research map / Probabilistic and scientific modeling / Variational and generative sampling

Flow-based Variational Mutual Information: Fast and Flexible Approximations

ICLR 2025 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Annealing and divergence-based variational objectives

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 flow-based variational approximations for mutual information bounds that are fast and flexible compared with standard variational distributions.

Problem

Mutual information is hard to compute in many settings; variational bounds require an approximate distribution, and the choice of that distribution is often restrictive.

Approach

Uses normalizing-flow-based variational distributions to build MI bounds, aiming to combine flexibility with fast computation. Only the abstract was available, so details beyond this are not stated.

Closest papers by meaning

• Understanding the Limitations of Variational Mutual Information Estimators (ICLR 2020 · similarity 0.92)
• Mutual Information Estimation via Normalizing Flows (NeurIPS 2024 · similarity 0.89)
• Mutual Information Estimation via $f$-Divergence and Data Derangements (NeurIPS 2024 · similarity 0.89)
• FMMI: Flow Matching Mutual Information Estimation (NeurIPS 2026 · similarity 0.88)
• Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.86)
• Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution (ICML 2024 · similarity 0.86)