Research map / Probabilistic and scientific modeling / Variational and generative sampling
Deep Probabilistic Programming
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 |
|---|---|---|---|
| remove analytic KL from the VAE (ablation) | VAE · Binarized MNIST | negative log-likelihood: ≤ 88.2 -> ≤ 89.4 | Hurt |
| use analytic entropy in the VAE (ablation) | VAE · Binarized MNIST | negative log-likelihood: ≤ 88.2 -> ≤ 88.1 | Helped |
| use a score function gradient in the VAE (ablation) | VAE · Binarized MNIST | negative log-likelihood: ≤ 88.2 -> ≤ 87.9 | Helped |
| use an IWAE objective with the hierarchical variational model (ablation) | Hierarchical variational model · Binarized MNIST | negative log-likelihood: ≤ 85.4 -> ≤ 85.2 | Helped |
| use Edward (GPU) rather than Stan (1 CPU) | Edward HMC · Covertype logistic regression | runtime (s): 171 -> 4.9 | Helped |
| use Edward (GPU) rather than PyMC3 (12 CPU) | Edward HMC · Covertype logistic regression | runtime (s): 30.0 -> 4.9 | Helped |
| use Edward (GPU) rather than handwritten TensorFlow (GPU) | Edward HMC · Covertype logistic regression | runtime (s): 5.0 -> 4.9 | No clear effect |
Closest papers by meaning
- Simple, Distributed, and Accelerated Probabilistic Programming (NeurIPS 2018 · similarity 0.91)
- A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics (NeurIPS 2024 · similarity 0.87)
- The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models (NeurIPS 2026 · similarity 0.86)
- On the Hardness of Approximating Distributions with Tractable Probabilistic Models (NeurIPS 2025 · similarity 0.85)
- Scaling Tractable Probabilistic Circuits: A Systems Perspective (ICML 2024 · similarity 0.85)
- On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models (NeurIPS 2024 · similarity 0.84)
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.