MIT Libraries logoDSpace@MIT

MIT
View Item 
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
  • DSpace@MIT Home
  • MIT Open Access Articles
  • MIT Open Access Articles
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Escaping saddle points in constrained optimization

Author(s)
Mokhtari, Aryan; Ozdaglar, Asuman E; Jadbabaie-Moghadam, Ali
Thumbnail
DownloadPublished version (464.0Kb)
Terms of use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Metadata
Show full item record
Abstract
In this paper, we study the problem of escaping from saddle points in smooth nonconvex optimization problems subject to a convex set C. We propose a generic framework that yields convergence to a second-order stationary point of the problem, if the convex set C is simple for a quadratic objective function. Specifically, our results hold if one can find a ρ-approximate solution of a quadratic program subject to C in polynomial time, where ρ < 1 is a positive constant that depends on the structure of the set C. Under this condition, we show that the sequence of iterates generated by the proposed framework reaches an (ε, γ)-second order stationary point (SOSP) in at most O(max{ε- 2 , ρ -3 γ -3 }) iterations. We further characterize the overall complexity of reaching an SOSP when the convex set C can be written as a set of quadratic constraints and the objective function Hessian has a specific structure over the convex set C. Finally, we extend our results to the stochastic setting and characterize the number of stochastic gradient and Hessian evaluations to reach an (ε, γ)-SOSP.
Date issued
2018-12
URI
https://hdl.handle.net/1721.1/121540
Department
Massachusetts Institute of Technology. Laboratory for Information and Decision Systems; Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Journal
32nd Conference on Neural Information Processing Systems (NeurIPS 2018)
Publisher
Neural Information Processing Systems Foundation
Citation
Mokhtari, Aryan, Asuman Ozdaglar and Ali Jadbabaie. "Escaping Saddle Points in Constrained Optimization." 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montreal Canada, Dec. 3-8, 2018.
Version: Final published version

Collections
  • MIT Open Access Articles

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

My Account

Login

Statistics

OA StatisticsStatistics by CountryStatistics by Department
MIT Libraries
PrivacyPermissionsAccessibilityContact us
MIT
Content created by the MIT Libraries, CC BY-NC unless otherwise noted. Notify us about copyright concerns.