Research map / Image generation / GANs
Exponential Family Estimation via Adversarial Dynamics Embedding
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 ADE instead of CD-15 | synthetic 2spirals estimation · 2spirals | MMD × 1e^-3: -0.45 -> -0.61 | Helped |
| use ADE instead of CD-15 | synthetic Banana estimation · Banana | MMD × 1e^-3: -0.31 -> -0.99 | Helped |
| use ADE instead of CD-15 | synthetic circles estimation · circles | MMD × 1e^-3: -0.83 -> -1.13 | Helped |
| use ADE instead of NF | synthetic cos estimation · cos | MMD × 1e^-3: 0.91 -> -0.55 | Helped |
| use ADE instead of CD-15 | synthetic Cosine estimation · Cosine | MMD × 1e^-3: 0.78 -> -1.09 | Helped |
| use ADE instead of NF | synthetic Funnel estimation · Funnel | MMD × 1e^-3: -0.92 -> -0.75 | Hurt |
| use ADE instead of CD-15 | synthetic swissroll estimation · swissroll | MMD × 1e^-3: 0.20 -> -0.36 | Helped |
| use ADE instead of NF | synthetic line estimation · line | MMD × 1e^-3: 0.39 -> -1.30 | Helped |
| use ADE instead of NF | synthetic moons estimation · moons | MMD × 1e^-3: 0.80 -> -1.10 | Helped |
| use ADE instead of CD-15 | synthetic Multiring estimation · Multiring | MMD × 1e^-3: -0.38 -> -1.02 | Helped |
| use ADE instead of CD-15 | synthetic pinwheel estimation · pinwheel | MMD × 1e^-3: -1.03 -> -0.95 | Hurt |
| use ADE instead of CD-15 | synthetic Ring estimation · Ring | MMD × 1e^-3: 0.12 -> -0.91 | Helped |
Closest papers by meaning
- A Computationally Efficient Method for Learning Exponential Family Distributions (NeurIPS 2021 · similarity 0.87)
- Learning Additive Exponential Family Graphical Models via $\ell_{2,1}$-norm Regularized M-Estimation (NeurIPS 2016 · similarity 0.86)
- Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions (NeurIPS 2021 · similarity 0.86)
- eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling (NeurIPS 2024 · similarity 0.85)
- Improving Adversarial Energy-Based Model via Diffusion Process (ICML 2024 · similarity 0.84)
- Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding (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.