Research map / Probabilistic and scientific modeling / Variational and generative sampling
Deconvolutional Density Network: Modeling Free-Form Conditional Distributions
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 the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Fish | log-likelihood: -1.38±0.14 -> -1.11±0.08 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Concrete | log-likelihood: -1.09±0.11 -> -0.58±0.14 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Energy | log-likelihood: -8.28±2.74 -> 1.87±0.23 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Parkinsons | log-likelihood: -1.81±0.09 -> -0.14±0.03 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Temperature | log-likelihood: -2.95±0.13 -> -0.71±0.07 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Air | log-likelihood: 0.47±0.32 -> 1.32±0.05 | Helped |
| use the deconvolutional density network instead of the strongest listed baseline | conditional density estimation · Skillcraft | log-likelihood: -8.54±0.43 -> -1.56±0.07 | Helped |
| add the variational layer (ablation) | DDN · Fish | log-likelihood: -2.24±0.18 -> -1.11±0.08 | Helped |
| add the variational layer (ablation) | DDN · Concrete | log-likelihood: -3.78±0.81 -> -0.58±0.14 | Helped |
| add the variational layer (ablation) | DDN · Energy | log-likelihood: -1.56±0.81 -> 1.87±0.23 | Helped |
| add the variational layer (ablation) | DDN · Parkinsons | log-likelihood: -0.17±0.05 -> -0.14±0.03 | Hurt |
| add the variational layer (ablation) | DDN · Temperature | log-likelihood: -0.84±0.07 -> -0.71±0.07 | Helped |
Closest papers by meaning
- Conditional Density Estimation with Histogram Trees (NeurIPS 2024 · similarity 0.87)
- Classification Diffusion Models: Revitalizing Density Ratio Estimation (NeurIPS 2024 · similarity 0.85)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.84)
- Neural Conditional Probability for Uncertainty Quantification (NeurIPS 2024 · similarity 0.84)
- DNA-SE: Towards Deep Neural-Nets Assisted Semiparametric Estimation (ICML 2024 · similarity 0.84)
- Generative Conditional Distributions by Neural (Entropic) Optimal Transport (ICML 2024 · similarity 0.83)
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.