Research map / Learning theory and algorithms / Matrix and tensor methods
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation
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 |
|---|---|---|---|
| Replace one-step graphical lasso with sequential adaptive convex programs (nonconvex SCAD-weighted relaxation, T=4) | Graphical nonconvex optimization estimator · Simulation random and band graphs, n=150/200, d=150 | Frobenius norm error of concentration matrix | Helped |
| Sequential convex approximation (contraction property) versus one-step convex estimator | Inverse correlation matrix estimator · Theory: spectral/Frobenius rate | estimation rate | Helped |
| Use sparsity-pattern-based spectral norm bound (Theorem 3.8) instead of sparsity-count bound | Inverse correlation matrix estimator · Theory: chain graphs | ratio of rate bounds ||M||_2^2/s | Helped |
Closest papers by meaning
- Nonconvex Sparse Graph Learning under Laplacian Constrained Graphical Model (NeurIPS 2020 · similarity 0.89)
- Speeding Up Latent Variable Gaussian Graphical Model Estimation via Nonconvex Optimization (NeurIPS 2017 · similarity 0.89)
- Conditional Matrix Flows for Gaussian Graphical Models (NeurIPS 2023 · similarity 0.87)
- A Completely Tuning-Free and Robust Approach to Sparse Precision Matrix Estimation (ICML 2022 · similarity 0.87)
- On the Statistical Limits of Convex Relaxations (ICML 2016 · similarity 0.87)
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.85)
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.