Corpus ID: 207870251

Iterative Algorithm for Discrete Structure Recovery

  title={Iterative Algorithm for Discrete Structure Recovery},
  author={C. Gao and A. Zhang},
  journal={arXiv: Statistics Theory},
We propose a general modeling and algorithmic framework for discrete structure recovery that can be applied to a wide range of problems. Under this framework, we are able to study the recovery of clustering labels, ranks of players, and signs of regression coefficients from a unified perspective. A simple iterative algorithm is proposed for discrete structure recovery, which generalizes methods including Lloyd's algorithm and the iterative feature matching algorithm. A linear convergence result… Expand
6 Citations
Scaled minimax optimality in high-dimensional linear regression: A non-convex algorithmic regularization approach.
  • 1
  • PDF
An $\ell_p$ theory of PCA and spectral clustering.
  • 1
  • PDF
Optimal Clustering in Anisotropic Gaussian Mixture Models
  • PDF
Optimal Full Ranking from Pairwise Comparisons
  • PDF
SDP Achieves Exact Minimax Optimality in Phase Synchronization
  • PDF


Optimal Variable Selection and Adaptive Noisy Compressed Sensing
  • 12
  • Highly Influential
  • PDF
Achieving Exact Cluster Recovery Threshold via Semidefinite Programming: Extensions
  • 107
Partial recovery bounds for clustering with the relaxed K-means
  • 31
  • PDF
Achieving Optimal Misclassification Proportion in Stochastic Block Models
  • 150
  • PDF
A General Framework for Bayes Structured Linear Models
  • 37
  • PDF
Information-theoretic limits on sparsity recovery in the high-dimensional and noisy setting
  • M. Wainwright
  • Mathematics, Computer Science
  • IEEE Trans. Inf. Theory
  • 2009
  • 228
  • PDF
Sharp optimal recovery in the Two Gaussian Mixture Model.
  • 8
Hard Thresholding Pursuit: An Algorithm for Compressive Sensing
  • S. Foucart
  • Mathematics, Computer Science
  • SIAM J. Numer. Anal.
  • 2011
  • 354
  • PDF
Exponential Error Rates of SDP for Block Models: Beyond Grothendieck’s Inequality
  • Yingjie Fei, Y. Chen
  • Computer Science, Mathematics
  • IEEE Transactions on Information Theory
  • 2019
  • 23
  • PDF