Corpus ID: 3353603

Nonconvex Matrix Factorization from Rank-One Measurements

@inproceedings{Li2019NonconvexMF,
  title={Nonconvex Matrix Factorization from Rank-One Measurements},
  author={Yuanxin Li and C. Ma and Y. Chen and Yuejie Chi},
  booktitle={AISTATS},
  year={2019}
}
  • Yuanxin Li, C. Ma, +1 author Yuejie Chi
  • Published in AISTATS 2019
  • Computer Science, Mathematics
    • We consider the problem of recovering low-rank matrices from random rank-one measurements, which spans numerous applications including covariance sketching, phase retrieval, quantum state tomography, and learning shallow polynomial neural networks, among others. Our approach is to directly estimate the low-rank factor by minimizing a nonconvex quadratic loss function via vanilla gradient descent, following a tailored spectral initialization. When the true rank is small, this algorithm is… CONTINUE READING
    View PDF on arXiv
    30 Citations
    Highly Influencial Citations
    3
    Background Citations
    12
    Methods Citations
    8
    30 Citations
    Citation Type

    Citation Type

    Beyond Procrustes: Balancing-free Gradient Descent for Asymmetric Low-Rank Matrix Sensing
    • 2
    • PDF
    Nonconvex Low-Rank Matrix Recovery with Arbitrary Outliers via Median-Truncated Gradient Descent
    • 15
    • PDF
    Low-Rank Matrix Recovery with Scaled Subgradient Methods: Fast and Robust Convergence Without the Condition Number
    • 1
    • PDF
    Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent
    • 7
    • PDF
    Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
    • 35
    • PDF
    Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
    • 132
    • PDF
    Noisy Matrix Completion : Understanding the Stability of Convex Relaxation via Nonconvex Optimization
    Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
    • 22
    • PDF
    Median-Truncated Gradient Descent: A Robust and Scalable Nonconvex Approach for Signal Estimation
    • 2
    • PDF
    Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation: Recent Theory and Fast Algorithms via Convex and Nonconvex Optimization
    • 64
    • PDF

    References

    SHOWING 1-10 OF 60 REFERENCES
    Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements
    • 23
    • PDF
    Nonconvex Low-Rank Tensor Completion from Noisy Data
    • 13
    Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimization
    • 35
    • PDF
    Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
    • 132
    • PDF
    Fast low-rank estimation by projected gradient descent: General statistical and algorithmic guarantees
    • 214
    • PDF
    Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements
    • E. Candès, Y. Plan
    • Mathematics, Computer Science
    • IEEE Transactions on Information Theory
    • 2011
    • 450
    ROP: Matrix Recovery via Rank-One Projections
    • 104
    • PDF
    Kaczmarz Method for Solving Quadratic Equations
    • 35
    • PDF
    Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval, Matrix Completion, and Blind Deconvolution
    • 133
    • PDF
    Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming
    • 164
    • PDF