Holder continuity of the steepest descent direction for multiobjective optimization
Benar Fux Svaiter

TL;DR
This paper investigates the continuity properties of the multiobjective steepest descent direction for smooth functions, establishing it as Holder continuous with exponent 1/2 and not Lipschitz continuous even for polynomial objectives.
Contribution
It provides a precise characterization of the Holder continuity of the steepest descent direction in multiobjective optimization, revealing its optimal exponent and limitations.
Findings
Steepest descent direction is Holder continuous with exponent 1/2.
The direction is not Lipschitz continuous for polynomial objectives.
Optimality of the Holder exponent is demonstrated.
Abstract
The aim of this manuscript is to characterize the continuity properties of the multiobjective steepest descent direction for smooth objective functions. We will show that this direction is Holder continuous with optimal exponent 1/2. In particular, this direction fails to be Lipschitz continuous even for polynomial objectives.
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
TopicsAdvanced Optimization Algorithms Research · Advanced Control Systems Optimization · Advanced Multi-Objective Optimization Algorithms
