Variable Quasi-Bregman Monotone Sequences
Quang Van Nguyen

TL;DR
This paper introduces variable quasi-Bregman monotone sequences, unifying existing concepts, and applies this framework to analyze the asymptotic behavior of proximal algorithms and convex feasibility problems in Banach spaces.
Contribution
It proposes a new unified notion of variable quasi-Bregman monotonicity and applies it to analyze convergence of proximal and feasibility algorithms.
Findings
Unified framework for variable quasi-Bregman monotone sequences
Analyzed asymptotic behavior of proximal iterations
Applied results to convex feasibility problems
Abstract
We introduce a notion of variable quasi-Bregman monotone sequence which unifies the notion of variable metric quasi-Fej\'er monotone sequences and that of Bregman monotone sequences. The results are applied to analyze the asymptotic behavior of proximal iterations based on variable Bregman distance and of algorithms for solving convex feasibility problems in reflexive real Banach spaces.
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
TopicsOptimization and Variational Analysis · Fixed Point Theorems Analysis · Advanced Optimization Algorithms Research
