Barrier Algorithms for Constrained Non-Convex Optimization

Abstract

In this paper we theoretically show that interior-point methods based on self-concordant barriers possess favorable global complexity beyond their standard application area of convex optimization. To do that we propose first- and second-order methods for non-convex optimization problems with general convex set constraints and linear constraints. Our methods attain a suitably defined class of approximate first- or second-order KKT points with the worst-case iteration complexity similar to unconstrained problems, namely $O(\varepsilon^{-2})$ (first-order) and $O(\varepsilon^{-3/2})$ (second-order), respectively.

Cite

Text

Dvurechensky and Staudigl. "Barrier Algorithms for Constrained Non-Convex Optimization." International Conference on Machine Learning, 2024.

Markdown

[Dvurechensky and Staudigl. "Barrier Algorithms for Constrained Non-Convex Optimization." International Conference on Machine Learning, 2024.](https://mlanthology.org/icml/2024/dvurechensky2024icml-barrier/)

BibTeX

@inproceedings{dvurechensky2024icml-barrier,
  title     = {{Barrier Algorithms for Constrained Non-Convex Optimization}},
  author    = {Dvurechensky, Pavel and Staudigl, Mathias},
  booktitle = {International Conference on Machine Learning},
  year      = {2024},
  pages     = {12190-12214},
  volume    = {235},
  url       = {https://mlanthology.org/icml/2024/dvurechensky2024icml-barrier/}
}