On Convergence of Binary Trust-Region Steepest Descent
Paul Manns, Mirko Hahn, Christian Kirches, Sven Leyffer and, Sebastian Sager

TL;DR
This paper improves the convergence analysis of binary trust-region steepest descent (BTR), showing it converges to stationary points and exhibits a regularizing effect, supported by computational validation and hybridization with CIA.
Contribution
The paper provides enhanced convergence results for BTR under a compactness assumption, linking it to CIA and demonstrating its regularizing properties.
Findings
BTR converges weakly-* to stationary points of the relaxed problem.
BTR has a regularizing effect on solutions.
Hybridization of CIA and BTR improves solution quality.
Abstract
Binary trust-region steepest descent (BTR) and combinatorial integral approximation (CIA) are two recently investigated approaches for the solution of optimization problems with distributed binary-/discrete-valued variables (control functions). We show improved convergence results for BTR by imposing a compactness assumption that is similar to the convergence theory of CIA. As a corollary we conclude that BTR also constitutes a descent algorithm on the continuous relaxation and its iterates converge weakly- to stationary points of the latter. We provide computational results that validate our findings. In addition, we observe a regularizing effect of BTR, which we explore by means of a hybridization of CIA and BTR.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComplexity and Algorithms in Graphs · Stochastic Gradient Optimization Techniques · Error Correcting Code Techniques
