Research map / Probabilistic and scientific modeling / Variational and generative sampling
Forward-Backward Gaussian Variational Inference via JKO in the Bures-Wasserstein Space
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 entropy JKO proximal step in place of the prior strongly log-concave approach | Stochastic FB-GVI · Strongly log-concave target | iteration complexity: Õ(β²d/(α²ε²)) -> Õ(βd/(αε²)) | Helped |
| Use FB-GVI rather than BWGD | Gaussian VI · Gaussian targets | maximum stable step size | Helped |
| Use (stochastic) FB-GVI rather than BWGD | Gaussian VI · Gaussian targets and Bayesian logistic regression | objective value | Mixed |
Closest papers by meaning
- Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold (ICLR 2025 · similarity 0.92)
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.90)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.89)
- Least squares variational inference (NeurIPS 2025 · similarity 0.88)
- Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families (NeurIPS 2024 · similarity 0.87)
- Symmetry Guarantees Statistic Recovery in 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.