Hessian barrier algorithms for non-convex conic optimization
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 (first-order) and (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.
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