A Greedy Anytime Algorithm for Sparse PCA

Guy Holtzman, Adam Soffer, Dan Vilenchik

Research output: Contribution to journalConference articlepeer-review


The taxing computational effort that is involved in solving some high-dimensional statistical problems, in particular problems involving non-convex optimization, has popularized the development and analysis of algorithms that run efficiently (polynomial-time) but with no general guarantee on statistical consistency. In light of the ever-increasing compute power and decreasing costs, a more useful characterization of algorithms is by their ability to calibrate the invested computational effort with various characteristics of the input at hand and with the available computational resources. We propose a new greedy algorithm for the ℓ0-sparse PCA problem which supports the calibration principle. We provide both a rigorous analysis of our algorithm in the spiked covariance model, as well as simulation results and comparison with other existing methods. Our findings show that our algorithm recovers the spike in SNR regimes where all polynomial-time algorithms fail while running in a reasonable parallel-time on a cluster.

Original languageAmerican English
Pages (from-to)1939-1956
Number of pages18
JournalProceedings of Machine Learning Research
StatePublished - 1 Jan 2020
Event33rd Conference on Learning Theory, COLT 2020 - Virtual, Online, Austria
Duration: 9 Jul 202012 Jul 2020


  • Sparse PCA
  • anytime algorithms
  • average case analysis
  • non-convex optimization

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'A Greedy Anytime Algorithm for Sparse PCA'. Together they form a unique fingerprint.

Cite this