Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational inference via Wasserstein gradient flows
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 Bures-Wasserstein gradient flow for Gaussian variational inference | Gaussian variational inference · Convex target distributions | convergence to the constrained KL minimizer | Helped |
| Discretize the Gaussian Bures-Wasserstein flow with stochastic gradients | Gaussian variational inference · Strongly log-concave, log-smooth targets | expected squared W2 distance to the Gaussian VI optimum: \exp(-\alpha kh) \, W_2^2(p_0, \hat \pi) + \frac{36dh}{\alpha^2} | Helped |
| Use Gaussian mixtures instead of a single Gaussian approximation | Gaussian particle method · Bimodal and Gaussian-mixture targets | approximation expressivity | Helped |
| Use the Gaussian-flow approximation rather than the Laplace approximation | Gaussian variational inference · Logistic target | KL divergence | Helped |
| Allow Gaussian-mixture component weights to change | Gaussian particle method · Variational inference with Gaussian mixtures | empirical performance | No clear effect |
Closest papers by meaning
- Theoretical Guarantees for Variational Inference with Fixed-Variance Mixture of Gaussians (ICML 2024 · similarity 0.92)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.91)
- Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold (ICLR 2025 · similarity 0.90)
- Generalized Variational Inference via Optimal Transport (AAAI 2024 · similarity 0.89)
- Particle Semi-Implicit Variational Inference (NeurIPS 2024 · similarity 0.89)
- Model-Informed Flows for Bayesian Inference (NeurIPS 2025 · similarity 0.89)
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.