Research map / Image generation / Fast diffusion sampling
Conditional score-based diffusion models for Bayesian inference in infinite dimensions
Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Condition the score-based diffusion model on observed data | Infinite-dimensional Bayesian linear inverse problems · Stylized conditional sampling example | discretization invariance | Improved |
| Use an amortized conditional score for posterior sampling | Linearized seismic imaging · Seismic imaging posterior | posterior sampling applicability | Improved |
| Condition the diffusion model on observations to represent the posterior | Conditional SDM · Stylized conditional distribution | multimodal distribution modeling | Improved |
| Use conditional denoising score matching to estimate the conditional score | Infinite-dimensional conditional SDM · Bayesian linear inverse problems | conditional score estimation | Improved |
| Use a conditional score with noiseless observations | Gaussian-prior conditional SDM · Noiseless observations | expected squared norm of the conditional score | Hurt |
Closest papers by meaning
- Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors (NeurIPS 2024 · similarity 0.92)
- Provable Posterior Sampling with Denoising Oracles via Tilted Transport (NeurIPS 2024 · similarity 0.91)
- Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior (ICLR 2025 · similarity 0.90)
- Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems (NeurIPS 2025 · similarity 0.90)
- Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction (NeurIPS 2024 · similarity 0.90)
- A Mixture-Based Framework for Guiding Diffusion Models (ICML 2025 · similarity 0.90)
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.
