Corpus ID: 207870251

Iterative Algorithm for Discrete Structure Recovery

  title={Iterative Algorithm for Discrete Structure Recovery},
  author={Chao 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
Scaled minimax optimality in high-dimensional linear regression: A non-convex algorithmic regularization approach.
An $\ell_p$ theory of PCA and spectral clustering.
Optimal Clustering in Anisotropic Gaussian Mixture Models
Optimal Full Ranking from Pairwise Comparisons
Optimal detection of the feature matching map in presence of noise and outliers
SDP Achieves Exact Minimax Optimality in Phase Synchronization


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