Research map / Learning theory and algorithms / Matrix and tensor methods
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
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 thresholding-MDMC with Newton-CG instead of QUIC | Graphical lasso · freeFlyingRobot-7 | runtime (sec): 28.9 vs 31.0 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | RGL · freeFlyingRobot-7 | runtime (sec): 12.1 vs 38.7 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | Graphical lasso · freeFlyingRobot-14 | runtime (sec): 23.5 vs 78.3 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | RGL · freeFlyingRobot-14 | runtime (sec): 19.0 vs 97.0 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | Graphical lasso · cryg10000 | runtime (sec): 17.3 vs 360.3 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | RGL · cryg10000 | runtime (sec): 18.5 vs 364.1 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | Graphical lasso · epb1 | runtime (sec): 81.6 vs 723.5 | Helped |
| Use thresholding-MDMC with Newton-CG instead of QUIC | RGL · epb1 | runtime (sec): 44.2 vs 1076.4 | Helped |
| Use thresholding-MDMC rather than QUIC for real-life graph problems | Graphical lasso and RGL · Real-life graphs with n≤1.5×10^4 | runtime: 11 times faster on average | Helped |
| Use Newton-CG MDMC rather than QUIC | MDMC solver · Banded patterns, n=1,000 to 200,000 | empirical time complexity: O(n^{1.1}) vs O(n^{2}) | Helped |
| Use Newton-CG MDMC rather than QUIC | MDMC solver · Banded pattern, n=200,000 | runtime: less than 33 minutes | Helped |
| Solve the full thresholding-MDMC procedure instead of QUIC | Graphical lasso and RGL · Real-life graphs, n≈2×10^5 | completion within time limit: a little more than an hour | Helped |
Closest papers by meaning
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.89)
- Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements (ICML 2025 · similarity 0.86)
- Non-Asymptotic Analysis Of Data Augmentation For Precision Matrix Estimation (NeurIPS 2025 · similarity 0.86)
- Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance (ICML 2024 · similarity 0.85)
- Efficient Sparse PCA via Block-Diagonalization (ICLR 2025 · similarity 0.85)
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements (NeurIPS 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.