Research map / Probabilistic and scientific modeling / Variational and generative sampling
f-Divergence Variational Inference
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 f_c1-VI instead of KL-VI | Bayesian VAE · Frey Face | cross-entropy reconstruction error: 160.85$\pm$.72 -> 160.52$\pm$.88 | Helped |
| Use f_c1-VI instead of KL-VI | Bayesian VAE · MNIST | cross-entropy reconstruction error: 59.06$\pm$.40 -> 59.60$\pm$.25 | Hurt |
| Use f_c1-VI instead of KL-VI | Bayesian VAE · Omniglot | cross-entropy reconstruction error: 109.62$\pm$.20 -> 107.13$\pm$.39 | Helped |
| Use f_c1-VI instead of KL-VI | Bayesian VAE · Caltech 101 | cross-entropy reconstruction error: 73.80$\pm$2.27 -> 74.87$\pm$2.56 | Hurt |
| Use f_c1-VI instead of KL-VI | Bayesian neural network · Stock | test RMSE: 3.85$\pm$1.12 -> 3.82$\pm$1.11 | Helped |
| Use f_c1-VI instead of KL-VI | Bayesian neural network · Fish Toxicity | test RMSE: 0.88$\pm$.04 -> 0.88$\pm$.03 | No clear effect |
| Use f_c1-VI instead of KL-VI | Bayesian neural network · Stock | test negative log-likelihood: -1.09$\pm$.04 -> -1.09$\pm$.04 | No clear effect |
Closest papers by meaning
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.89)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.88)
- Globally Convergent Variational Inference (NeurIPS 2024 · similarity 0.88)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.87)
- Least squares variational inference (NeurIPS 2025 · similarity 0.87)
- Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inference (NeurIPS 2026 · similarity 0.87)
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.