Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers

Yifan Chen Yuejiao Sun University of California, Los Angeles Wotao Yin University of California, Los Angeles

Optimization and Control mathscidoc:2005.27001

Mathematical Programming, 2019
Many optimization algorithms converge to stationary points. When the underlying problem is nonconvex, they may get trapped at local minimizers and occasionally stagnate near saddle points. We propose the Run-and-Inspect Method, which adds an “inspect” phase to existing algorithms that helps escape from non-global stationary points. The inspection samples a set of points in a radius R around the current point. When a sample point yields a sufficient decrease in the objective, we resume an existing algorithm from that point. If no sufficient decrease is found, the current point is called an approximate R-local minimizer. We show that an R-local minimizer is globally optimal, up to a specific error depending on R, if the objective function can be implicitly decomposed into a smooth convex function plus a restricted function that is possibly nonconvex, nonsmooth. Therefore, for such nonconvex objective functions, verifying global optimality is fundamentally easier. For high-dimensional problems, we introduce blockwise inspections to overcome the curse of dimensionality while still maintaining optimality bounds up to a factor equal to the number of blocks. Our method performs well on a set of artificial and realistic nonconvex problems by coupling with gradient descent, coordinate descent, EM, and prox-linear algorithms.
R-local minimizer, Run-and-Inspect Method, nonconvex optimization, global minimum, global optimality
[ Download ] [ 2020-05-03 15:32:49 uploaded by sunyj ] [ 407 downloads ] [ 0 comments ]
@inproceedings{yifan2019run-and-inspect,
  title={Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers},
  author={Yifan Chen, Yuejiao Sun, and Wotao Yin},
  url={http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20200503153249478617663},
  booktitle={Mathematical Programming},
  year={2019},
}
Yifan Chen, Yuejiao Sun, and Wotao Yin. Run-and-Inspect Method for Nonconvex Optimization and Global Optimality Bounds for R-Local Minimizers. 2019. In Mathematical Programming. http://archive.ymsc.tsinghua.edu.cn/pacm_paperurl/20200503153249478617663.
Please log in for comment!
 
 
Contact us: office-iccm@tsinghua.edu.cn | Copyright Reserved