Understanding FISTA's weak convergence: A step-by-step introduction to the 2025 milestone
Heinz H. Bauschke, Walaa M. Moursi

TL;DR
This paper provides a clear, step-by-step introduction to the recent proof of weak convergence of FISTA iterates, a milestone achieved in 2025 that enhances understanding of this influential optimization algorithm.
Contribution
It offers an accessible, self-contained explanation of the 2025 proof of FISTA's weak convergence, clarifying a significant theoretical advancement.
Findings
Proof of weak convergence of FISTA iterates in 2025
Enhanced understanding of FISTA's theoretical properties
Clarification of the convergence behavior of FISTA
Abstract
Beck and Teboulle's FISTA for finding the minimizer of the sum of two convex functions is one of the most important algorithms of the past decades. While function value convergence of the iterates was known, the actual convergence of the iterates remained elusive until October 2025 when Jang and Ryu, as well as Bo\c{t}, Fadili, and Nguyen proved weak convergence. In this paper, we provide a gentle self-contained introduction to the proof of their remarkable result.
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
TopicsStochastic Gradient Optimization Techniques · Optimization and Variational Analysis · Risk and Portfolio Optimization
