Abstract
The Condat-Vũ algorithm is a widely used primal-dual method for optimizing composite objectives of three functions. Several algorithms for optimizing composite objectives of two functions are special cases of Condat-Vũ, including proximal gradient descent (PGD). It is well-known that PGD exhibits suboptimal performance, and a simple adjustment to PGD can accelerate its convergence rate from O(1/T) to O(1/T2) on convex objectives, and this accelerated rate is optimal. In this work, we show that a simple adjustment to the Condat-Vũ algorithm allows it to recover accelerated PGD (APGD) as a special case, instead of PGD. We prove that this accelerated Condat--Vũ algorithm achieves optimal convergence rates and significantly outperforms the traditional Condat-Vũ algorithm in regimes where the Condat--Vũ algorithm approximates the dynamics of PGD. We demonstrate the effectiveness of our approach in various applications in machine learning and computational imaging.
| Original language | English |
|---|---|
| Pages (from-to) | 2053-2417 |
| Number of pages | 34 |
| Journal | SIAM Journal on Imaging Sciences |
| Volume | 17 |
| Issue number | 4 |
| Early online date | 15 Oct 2024 |
| DOIs | |
| Publication status | Published - Dec 2024 |
Fingerprint
Dive into the research topics of 'Practical Acceleration of the Condat–Vũ Algorithm'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver