Research map / Learning theory and algorithms / Matrix and tensor methods
Non-Iterative Recovery From Nonlinear Observations Using Generative Models
Check 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 |
|---|---|---|---|
| replace iterative projected recovery with OneShot | 1-bit CS with generative priors · MNIST | cosine similarity | Helped |
| replace iterative projected recovery with OneShot | 1-bit CS with generative priors · CelebA | cosine similarity | Helped |
| replace iterative projected recovery with OneShot | cubic CS with generative priors · MNIST | cosine similarity | Helped |
| replace iterative projected recovery with OneShot | cubic CS with generative priors · CelebA | cosine similarity | No clear effect |
| use GAN-based non-iterative projection instead of gradient-based projection (ablation) | OneShot · 1-bit MNIST | cosine similarity | Hurt |
| use GAN-based non-iterative projection instead of gradient-based projection (ablation) | OneShot · 1-bit CelebA | cosine similarity | No clear effect |
| use GAN-based non-iterative projection instead of gradient-based projection (ablation) | OneShot · cubic MNIST | cosine similarity | Hurt |
| use GAN-based non-iterative projection instead of gradient-based projection (ablation) | OneShot · cubic CelebA | cosine similarity | No clear effect |
| use one projected-gradient step rather than subsequent PGD iterations (ablation) | cubic recovery · CelebA | cosine similarity | No clear effect |
| use non-iterative GAN-based projection instead of iterative gradient-based projection (ablation) | OneShot · MNIST and CelebA, 1-bit and cubic | time (secs) per reconstruction: 0.34 -> 0.03 (1-bit MNIST); 130.63 -> 0.61 (1-bit CelebA); 0.61 -> 0.03 (cubic MNIST); 128.89 -> 0.66 (cubic CelebA) | Helped |
Closest papers by meaning
- A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing (NeurIPS 2023 · similarity 0.91)
- Efficient Algorithms for Non-gaussian Single Index Models with Generative Priors (AAAI 2024 · similarity 0.90)
- Modeling Sparse Deviations for Compressed Sensing using Generative Models (ICML 2018 · similarity 0.90)
- Compressed Sensing using Generative Models (ICML 2017 · similarity 0.90)
- Learning Single Index Models with Diffusion Priors (ICML 2025 · similarity 0.89)
- Sparse Bayesian Generative Modeling for Compressive Sensing (NeurIPS 2024 · 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.