Dualities for non-Euclidean smoothness and strong convexity under the light of generalized conjugacy
Emanuel Laude, Andreas Themelis, Panagiotis Patrinos

TL;DR
This paper explores duality relationships for non-Euclidean notions of smoothness and strong convexity in optimization, introducing anisotropic concepts and generalized conjugacy to extend classical dualities.
Contribution
It introduces anisotropic strong convexity and smoothness as dual notions under generalized conjugacy, addressing open problems in non-Euclidean dualities.
Findings
Dualities are established under generalized conjugacy.
Counterexamples show inclusions are proper in non-Euclidean cases.
New notions extend classical Euclidean duality concepts.
Abstract
Relative smoothness and strong convexity have recently gained considerable attention in optimization. These notions are generalizations of the classical Euclidean notions of smoothness and strong convexity that are known to be dual to each other. However, conjugate dualities for non-Euclidean relative smoothness and strong convexity remain an open problem as noted earlier by Lu, Freund and Nesterov [SIAM J. Optim., 28 (2018), pp. 333-354]. In this paper we address this question by introducing the notions of anisotropic strong convexity and smoothness as the respective dual counterparts. The dualities are developed under the light of generalized conjugacy which leads us embed the anticipated dual notions within the superclasses of certain upper and lower envelopes. In contrast to the Euclidean case these inclusions are proper in general as showcased by means of counterexamples.
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
TopicsPhagocytosis and Immune Regulation · Sparse and Compressive Sensing Techniques · Optimization and Variational Analysis
