Research map / Probabilistic and scientific modeling / Variational and generative sampling
Instance-Optimal Compressed Sensing via Posterior Sampling
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 posterior sampling via Langevin dynamics instead of MAP | Glow compressed sensing · CelebA-HQ | per-pixel reconstruction error | Helped |
| Use posterior sampling via Langevin dynamics instead of MAP | NCSNv2 compressed sensing · FFHQ | per-pixel reconstruction error | Helped |
| Use posterior sampling via Langevin dynamics instead of Deep-Decoder | FFHQ compressed sensing · FFHQ | per-pixel reconstruction error | No clear effect |
| Use posterior sampling via Langevin dynamics instead of MAP | Glow inpainting · CelebA-HQ inpainting | reconstruction diversity | Helped |
| Select hyperparameters to minimize validation reconstruction error rather than maximize posterior likelihood | MAP · CelebA-HQ compressed sensing | reconstruction accuracy | Helped |
Closest papers by meaning
- Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing (NeurIPS 2026 · similarity 0.94)
- Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priors (ICML 2020 · similarity 0.91)
- Towards Sample-Optimal Compressive Phase Retrieval with Sparse and Generative Priors (NeurIPS 2021 · similarity 0.91)
- Sparse Bayesian Generative Modeling for Compressive Sensing (NeurIPS 2024 · similarity 0.90)
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions (NeurIPS 2025 · similarity 0.89)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 2025 · similarity 0.86)
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.