AI Paper Atlas

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

Learning Gaussian Conditional Distributions using Neural Ratio Estimation is Hard

Pierre Glaser, Arthur Gretton

NeurIPS 2026 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation

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.

Theoretical and empirical study showing that neural ratio estimation (NRE) is statistically inefficient when learning Gaussian conditional distributions.

Problem

Statistical efficiency of neural ratio estimation for simulation-based posterior estimation is poorly understood; the paper asks how many simulations NRE needs to obtain accurate posteriors.

Approach

Analyzes NRE's sample complexity specifically for Gaussian conditional distributions and argues, per the title, that learning these with NRE is hard (statistically inefficient). Full details are not available beyond the abstract.

Experimental setup

Builds on: neural ratio estimation

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy