Research map / Probabilistic and scientific modeling / Variational and generative sampling
Generative Particle Variational Inference via Estimation of Functional Gradients
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 GPVI instead of amortized SVGD | Generative particle variational inference · 5D Gaussian density estimation | Σ error: 0.58 -> 0.14 | Helped |
| Use GPVI instead of amortized GFSF | Generative particle variational inference · 5D Gaussian density estimation | Σ error: 0.21 -> 0.14 | Helped |
| Use GPVI instead of amortized KSD | Generative particle variational inference · 5D Gaussian density estimation | Σ error: 1.68 -> 0.14 | Helped |
| Use GPVI instead of amortized SVGD | Bayesian linear regression · Bayesian linear regression | Σ error: 0.161 -> 0.133 | Helped |
| Use GPVI instead of HMC | Bayesian linear regression · Bayesian linear regression | Σ error: 0.181 -> 0.133 | Helped |
| Use GPVI instead of amortized SVGD | Generative particle variational inference · MNIST open-category | AUC: 0.974 -> 0.989 | Helped |
| Use GPVI instead of amortized GFSF | Generative particle variational inference · MNIST open-category | AUC: 0.978 -> 0.989 | Helped |
| Use GPVI instead of amortized SVGD | Generative particle variational inference · CIFAR-10 open-category | AUC: 0.637 -> 0.677 | Helped |
| Use GPVI instead of amortized GFSF | Generative particle variational inference · CIFAR-10 open-category | AUC: 0.580 -> 0.677 | Helped |
| Back-propagate the exact generator functional gradient rather than the amortized SVGD particle gradient | Generative sampler · 4-class multimodal classification | Predictive uncertainty in regions without training data | Helped |
Closest papers by meaning
- Particle Semi-Implicit Variational Inference (NeurIPS 2024 · similarity 0.90)
- Functional Gradient Flows for Constrained Sampling (NeurIPS 2024 · similarity 0.90)
- Kernel Semi-Implicit Variational Inference (ICML 2024 · similarity 0.89)
- EigenVI: score-based variational inference with orthogonal function expansions (NeurIPS 2024 · similarity 0.88)
- Revisiting Unbiased Implicit Variational Inference (ICML 2025 · similarity 0.88)
- GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework (AAAI 2024 · similarity 0.88)
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.