Research map / Probabilistic and scientific modeling / Variational and generative sampling
Density estimation using Real NVP
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use Real NVP instead of PixelRNN | CIFAR-10 density estimation · CIFAR-10 test | bits/dim: 3.00 -> 3.49 | Hurt |
| Use Real NVP instead of PixelRNN | Imagenet (32 × 32) density estimation · Imagenet (32 × 32) validation | bits/dim: 3.86 -> 4.28 | Hurt |
| Use Real NVP instead of PixelRNN | Imagenet (64 × 64) density estimation · Imagenet (64 × 64) validation | bits/dim: 3.63 -> 3.98 | Hurt |
| Use batch normalization with moving-average statistics | Real NVP training with very small minibatches · Unspecified | training stability | Helped |
| Use batch normalization in coupling layers | Real NVP · Unspecified | training stability | Helped |
Closest papers by meaning
- Neural Inverse Transform Sampler (ICML 2022 · similarity 0.86)
- Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling (ICML 2020 · similarity 0.84)
- Unsupervised Learning for Robust Fitting: A Reinforcement Learning Approach (CVPR 2021 · similarity 0.83)
- Nonparametric Estimation of a Factorizable Density using Diffusion Models (NeurIPS 2026 · similarity 0.83)
- Exploring Diffusion Time-steps for Unsupervised Representation Learning (ICLR 2024 · similarity 0.83)
- Density Ratio Estimation with Conditional Probability Paths (ICML 2025 · similarity 0.82)
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.