Research map / Learning theory and algorithms / Matrix and tensor methods
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
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 an expansive-Gaussian generative network prior and minimize nonlinear least squares over its latent input | Spiked Wishart recovery · Spiked Wishart model | reconstruction error | Helped |
| Use an expansive-Gaussian generative network prior and minimize nonlinear least squares over its latent input | Spiked Wigner recovery · Spiked Wigner model | reconstruction error | Helped |
| Run gradient descent from both a random initialization and its negation, then select the result with lower loss | Generative-prior spiked matrix recovery · Synthetic Wishart and Wigner experiments | reconstruction error | Helped |
Closest papers by meaning
- The spiked matrix model with generative priors (NeurIPS 2019 · similarity 0.91)
- Generative Principal Component Analysis (ICLR 2022 · similarity 0.90)
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.87)
- How many measurements are enough? Bayesian recovery in inverse problems with general distributions (NeurIPS 2025 · similarity 0.87)
- Sparse Bayesian Generative Modeling for Compressive Sensing (NeurIPS 2024 · similarity 0.86)
- Efficient Algorithms for Non-gaussian Single Index Models with Generative Priors (AAAI 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.