Formalization of Complexity Analysis of the First-order Algorithms for Convex Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Chenyi, Wang, Ziyu, He, Wanyi, Wu, Yuxuan, Xu, Shengyang, Wen, Zaiwen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910536350826496
author Li, Chenyi
Wang, Ziyu
He, Wanyi
Wu, Yuxuan
Xu, Shengyang
Wen, Zaiwen
author_facet Li, Chenyi
Wang, Ziyu
He, Wanyi
Wu, Yuxuan
Xu, Shengyang
Wen, Zaiwen
contents The convergence rate of various first-order optimization algorithms is a pivotal concern within the numerical optimization community, as it directly reflects the efficiency of these algorithms across different optimization problems. Our goal is making a significant step forward in the formal mathematical representation of optimization techniques using the Lean4 theorem prover. We first formalize the gradient for smooth functions and the subgradient for convex functions on a Hilbert space, laying the groundwork for the accurate formalization of algorithmic structures. Then, we extend our contribution by proving several properties of differentiable convex functions that have not yet been formalized in Mathlib. Finally, a comprehensive formalization of these algorithms is presented. These developments are not only noteworthy on their own but also serve as essential precursors to the formalization of a broader spectrum of numerical algorithms and their applications in machine learning as well as many other areas.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11437
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Formalization of Complexity Analysis of the First-order Algorithms for Convex Optimization
Li, Chenyi
Wang, Ziyu
He, Wanyi
Wu, Yuxuan
Xu, Shengyang
Wen, Zaiwen
Optimization and Control
Numerical Analysis
G.1.6
The convergence rate of various first-order optimization algorithms is a pivotal concern within the numerical optimization community, as it directly reflects the efficiency of these algorithms across different optimization problems. Our goal is making a significant step forward in the formal mathematical representation of optimization techniques using the Lean4 theorem prover. We first formalize the gradient for smooth functions and the subgradient for convex functions on a Hilbert space, laying the groundwork for the accurate formalization of algorithmic structures. Then, we extend our contribution by proving several properties of differentiable convex functions that have not yet been formalized in Mathlib. Finally, a comprehensive formalization of these algorithms is presented. These developments are not only noteworthy on their own but also serve as essential precursors to the formalization of a broader spectrum of numerical algorithms and their applications in machine learning as well as many other areas.
title Formalization of Complexity Analysis of the First-order Algorithms for Convex Optimization
topic Optimization and Control
Numerical Analysis
G.1.6
url https://arxiv.org/abs/2403.11437