Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
 
conference paper

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

Kavis, Ali  
•
Levy, Kfir Yehuda
•
Bach, Francis
Show more
2019
Advances In Neural Information Processing Systems 32 (Nips 2019)
33rd Conference on Neural Information Processing Systems (NeurIPS)

We propose a novel adaptive, accelerated algorithm for the stochastic constrained convex optimization setting. Our method, which is inspired by the Mirror-Prox method, \emph{simultaneously} achieves the optimal rates for smooth/non-smooth problems with either deterministic/stochastic first-order oracles. This is done without any prior knowledge of the smoothness nor the noise properties of the problem. To the best of our knowledge, this is the first adaptive, unified algorithm that achieves the optimal rates in the constrained setting. We demonstrate the practical performance of our framework through extensive numerical experiments.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

unixgrad-a-universal-adaptive-algorithm-with-optimal-guarantees-for-constrained-optimization.pdf

Type

Postprint

Version

http://purl.org/coar/version/c_ab4af688f83e57aa

Access type

openaccess

License Condition

Copyright

Size

914.67 KB

Format

Adobe PDF

Checksum (MD5)

8d1b9ad7b62918c8bc335f53a543b42f

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés