Low-Rank Structure in Machine Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Exploiting low-rank structure for efficiency and generalization in machine learning and reinforcement learning.

Low-Rank Structure in Machine Learning: 10 key papers

1. Exact Matrix Completion via Convex Optimization
   Candes and Recht. arXiv 2008.
2. A Simpler Approach to Matrix Completion
   Recht. arXiv 2009.
3. Matrix Completion from a Few Entries
   Keshavan et al. arXiv 2009.
4. Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
   Recht et al. arXiv 2007.
5. Low-rank Solutions of Linear Matrix Equations via Procrustes Flow
   Tu et al. arXiv 2015.
6. LoRA: Low-Rank Adaptation of Large Language Models
   Hu et al. arXiv 2021.
7. Rank-Sparsity Incoherence for Matrix Decomposition
   Chandrasekaran et al. arXiv 2009.
8. Robust Principal Component Analysis?
   Candes et al. arXiv 2009.
9. The Power of Convex Relaxation: Near-Optimal Matrix Completion
   Candes and Tao. arXiv 2009.
10. Non-convex Robust PCA
    Netrapalli et al. arXiv 2014.

Related reading lists

• Spectral Methods in Machine Learning
• Block MDPs & Latent State Discovery
• Optimal Control & LQR/LQG
• System Identification & Learning Dynamical Systems
• Causal Discovery & Structure Learning
• Linear MDPs & Linear Function Approximation
• Physics-Informed Machine Learning & Scientific ML
• Concentration Inequalities & Empirical Processes