ICML 2019oral27 citations

Multi-Frequency Phase Synchronization

Tingran Gao, Zhizhen Zhao

Abstract

We propose a novel formulation for phase synchronization—the statistical problem of jointly estimating alignment angles from noisy pairwise comparisons—as a nonconvex optimization problem that enforces consistency among the pairwise comparisons in multiple frequency channels. Inspired by harmonic retrieval in signal processing, we develop a simple yet efficient two-stage algorithm that leverages the multi-frequency information. We demonstrate in theory and practice that the proposed algorithm significantly outperforms state-of-the-art phase synchronization algorithms, at a mild computational costs incurred by using the extra frequency channels. We also extend our algorithmic framework to general synchronization problems over compact Lie groups.

BibTeX
@InProceedings{pmlr-v97-gao19f,
  title = 	 {Multi-Frequency Phase Synchronization},
  author =       {Gao, Tingran and Zhao, Zhizhen},
  booktitle = 	 {Proceedings of the 36th International Conference on Machine Learning},
  pages = 	 {2132--2141},
  year = 	 {2019},
  editor = 	 {Chaudhuri, Kamalika and Salakhutdinov, Ruslan},
  volume = 	 {97},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {09--15 Jun},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v97/gao19f/gao19f.pdf},
  url = 	 {https://proceedings.mlr.press/v97/gao19f.html},
  abstract = 	 {We propose a novel formulation for phase synchronization—the statistical problem of jointly estimating alignment angles from noisy pairwise comparisons—as a nonconvex optimization problem that enforces consistency among the pairwise comparisons in multiple frequency channels. Inspired by harmonic retrieval in signal processing, we develop a simple yet efficient two-stage algorithm that leverages the multi-frequency information. We demonstrate in theory and practice that the proposed algorithm significantly outperforms state-of-the-art phase synchronization algorithms, at a mild computational costs incurred by using the extra frequency channels. We also extend our algorithmic framework to general synchronization problems over compact Lie groups.}
}
Multi-Frequency Phase Synchronization · ICML 2019