Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908780148555776 |
|---|---|
| author | Rotaru, Teodor Patrinos, Panagiotis Glineur, François |
| author_facet | Rotaru, Teodor Patrinos, Panagiotis Glineur, François |
| contents | We investigate a difference-of-convex (DC) formulation where the second term is allowed to be weakly convex. We examine the precise behavior of a single iteration of the difference-of-convex algorithm (DCA), providing a tight characterization of the objective function decrease, distinguishing between six distinct parameter regimes.
Our proofs, inspired by the performance estimation framework, are notably simplified compared to related prior research. We subsequently derive sublinear convergence rates for the DCA towards critical points, assuming at least one of the functions is smooth.
Additionally, we explore the underexamined equivalence between proximal gradient descent (PGD) and DCA iterations, demonstrating how DCA, a parameter-free algorithm, without the need for a stepsize, serves as a tool for studying the exact convergence rates of PGD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04486 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent Rotaru, Teodor Patrinos, Panagiotis Glineur, François Optimization and Control We investigate a difference-of-convex (DC) formulation where the second term is allowed to be weakly convex. We examine the precise behavior of a single iteration of the difference-of-convex algorithm (DCA), providing a tight characterization of the objective function decrease, distinguishing between six distinct parameter regimes. Our proofs, inspired by the performance estimation framework, are notably simplified compared to related prior research. We subsequently derive sublinear convergence rates for the DCA towards critical points, assuming at least one of the functions is smooth. Additionally, we explore the underexamined equivalence between proximal gradient descent (PGD) and DCA iterations, demonstrating how DCA, a parameter-free algorithm, without the need for a stepsize, serves as a tool for studying the exact convergence rates of PGD. |
| title | Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2503.04486 |