English

Hessian barrier algorithms for non-convex conic optimization

Optimization and Control 2022-10-18 v2

Abstract

We consider the minimization of a continuous function over the intersection of a regular cone with an affine set via a new class of adaptive first- and second-order optimization methods, building on the Hessian-barrier techniques introduced in [Bomze, Mertikopoulos, Schachinger, and Staudigl, Hessian barrier algorithms for linearly constrained optimization problems, SIAM Journal on Optimization, 2019]. Our approach is based on a potential-reduction mechanism and attains a suitably defined class of approximate first- or second-order KKT points with the optimal worst-case iteration complexity O(ε2)O(\varepsilon^{-2}) (first-order) and O(ε3/2)O(\varepsilon^{-3/2}) (second-order), respectively. A key feature of our methodology is the use of self-concordant barrier functions to construct strictly feasible iterates via a disciplined decomposition approach and without sacrificing on the iteration complexity of the method. To the best of our knowledge, this work is the first which achieves these worst-case complexity bounds under such weak conditions for general conic constrained optimization problems.

Keywords

Cite

@article{arxiv.2111.00100,
  title  = {Hessian barrier algorithms for non-convex conic optimization},
  author = {Pavel Dvurechensky and Mathias Staudigl},
  journal= {arXiv preprint arXiv:2111.00100},
  year   = {2022}
}

Comments

significantly revised new version; added result on anytime convergence results

R2 v1 2026-06-24T07:18:37.684Z