Research map / Learning theory and algorithms / Matrix and tensor methods
Optimal Algorithms for the Inhomogeneous Spiked Wigner Model
Alexander Pak, Justin Ko, Florent Krzakala
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 |
|---|---|---|---|
| Adapt the spectral method to the inhomogeneous noise profile | Spectral recovery for the inhomogeneous spiked Wigner model · Inhomogeneous spiked Wigner | Detectability threshold: λ=1 | Improved |
| Use AMP with Bayes-optimal denoisers | Inhomogeneous spiked Wigner · Inhomogeneous spiked Wigner | Bayes-optimal fixed-point agreement | Improved |
| Use a sparse prior in the statistical-to-computational gap regime | Inhomogeneous spiked Wigner · Sparse-prior inhomogeneous spiked Wigner | Signal recovery below the algorithmic threshold: λ<1 | Mixed |
Closest papers by meaning
- Spectral Phase Transition and Optimal PCA in Block-Structured Spiked Models (ICML 2024 · similarity 0.91)
- Fluctuations of the largest eigenvalues of transformed spiked Wigner matrices (ICML 2025 · similarity 0.84)
- Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods (NeurIPS 2024 · similarity 0.83)
- Optimal Spectral Transitions in High-Dimensional Multi-Index Models (NeurIPS 2025 · similarity 0.81)
- Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm (NeurIPS 2024 · similarity 0.81)
- Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models (NeurIPS 2024 · similarity 0.81)
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.
