Welcome to the homepage of the

Mathematical Optimization for Data Science Group

Department of Mathematics and Computer Science, Saarland University, Germany

From Learning to Optimize to Learning Optimization Algorithms

C. Castera and P. Ochs

Abstract:
Towards designing learned optimization algorithms that are usable beyond their training setting, we identify key principles that classical algorithms obey, but have up to now, not been used for Learning to Optimize (L2O). Following these principles, we provide a general design pipeline, taking into account data, architecture and learning strategy, and thereby enabling a synergy between classical optimization and L2O, resulting in a philosophy of Learning Optimization Algorithms. As a consequence our learned algorithms perform well far beyond problems from the training distribution. We demonstrate the success of these novel principles by designing a new learning-enhanced BFGS algorithm and provide numerical experiments evidencing its adaptation to many settings at test time.
pdf Bibtex arXiv
Latest update: 28.05.2024
Citation:
C. Castera, P. Ochs:
From Learning to Optimize to Learning Optimization Algorithms. [pdf]
Technical Report, ArXiv e-prints, arXiv:2405.18222, 2024.
Bibtex:
@techreport{CO24,
  title        = {From Learning to Optimize to Learning Optimization Algorithms},
  author       = {C. Castera and P. Ochs},
  year         = {2024},
  journal      = {ArXiv e-prints, arXiv:2405.18222},
}


MOP Group
©2017-2025
The author is not
responsible for
the content of
external pages.