Research map / Probabilistic and scientific modeling / Variational and generative sampling
Neural Inverse Transform Sampler
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 continuous NITS-CONV instead of Flow++ | CIFAR-10 density estimation · CIFAR-10 | negative log likelihood (bits/dim): 3.08 -> 2.97 | Helped |
| Use DISCRETE NITS-CONV instead of PixelSNAIL | CIFAR-10 density estimation · CIFAR-10 | negative log likelihood (bits/dim): 2.85 -> 2.94 | Hurt |
| Use NITS-MLP instead of NSF | POWER density estimation · POWER | test log likelihood: 0.66 $\pm$ 0.01 -> 0.66 $\pm$ 0.01 | No clear effect |
| Use NITS-MLP instead of NSF | GAS density estimation · GAS | test log likelihood: 13.09 $\pm$ 0.02 -> 13.20 $\pm$ 0.01 | Helped |
| Use NITS-MLP instead of NSF | HEPMASS density estimation · HEPMASS | test log likelihood: -14.01 $\pm$ 0.03 -> -12.93 $\pm$ 0.02 | Helped |
| Use NITS-MLP instead of NAF | MINIBOONE density estimation · MINIBOONE | test log likelihood: -8.86 $\pm$ 0.15 -> -10.85 $\pm$ 0.02 | Hurt |
| Use NITS-CONV instead of NAF | BSDS300 density estimation · BSDS300 | test log likelihood: 157.73 $\pm$ 0.04 -> 163.35 $\pm$ 0.22 | Helped |
Closest papers by meaning
- DEFT: Efficient Fine-tuning of Diffusion Models by Learning the Generalised $h$-transform (NeurIPS 2024 · similarity 0.87)
- Nonparametric Estimation of a Factorizable Density using Diffusion Models (NeurIPS 2026 · similarity 0.87)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.86)
- Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics (ICLR 2025 · similarity 0.86)
- Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models (ICML 2025 · similarity 0.86)
- SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems (ICML 2025 · 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.