ProxiCBO: A Provably Convergent Consensus-Based Method for Composite Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914481759584256 |
|---|---|
| author | Zhang, Haoyu Ma, Yanting Kitichotkul, Ruangrawee Rapp, Joshua Boufounos, Petros |
| author_facet | Zhang, Haoyu Ma, Yanting Kitichotkul, Ruangrawee Rapp, Joshua Boufounos, Petros |
| contents | This paper introduces an interacting-particle optimization method tailored to possibly non-convex composite optimization problems, which arise widely in signal processing. The proposed method, \emph{ProxiCBO}, integrates consensus-based optimization (CBO) with proximal gradient techniques to handle challenging optimization landscapes and exploit the composite structure of the objective function. We establish global convergence guarantees for the continuous-time finite-particle dynamics and develop an alternating update scheme for efficient practical implementation. Simulation results for signal processing tasks, including signal recovery from one-bit quantized measurements and parameter estimation from single-photon lidar data, demonstrate that ProxiCBO outperforms existing proximal gradient methods and CBO methods in terms of both accuracy and particle-efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_09789 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ProxiCBO: A Provably Convergent Consensus-Based Method for Composite Optimization Zhang, Haoyu Ma, Yanting Kitichotkul, Ruangrawee Rapp, Joshua Boufounos, Petros Optimization and Control Numerical Analysis 90C56, 65C35, 82C22 This paper introduces an interacting-particle optimization method tailored to possibly non-convex composite optimization problems, which arise widely in signal processing. The proposed method, \emph{ProxiCBO}, integrates consensus-based optimization (CBO) with proximal gradient techniques to handle challenging optimization landscapes and exploit the composite structure of the objective function. We establish global convergence guarantees for the continuous-time finite-particle dynamics and develop an alternating update scheme for efficient practical implementation. Simulation results for signal processing tasks, including signal recovery from one-bit quantized measurements and parameter estimation from single-photon lidar data, demonstrate that ProxiCBO outperforms existing proximal gradient methods and CBO methods in terms of both accuracy and particle-efficiency. |
| title | ProxiCBO: A Provably Convergent Consensus-Based Method for Composite Optimization |
| topic | Optimization and Control Numerical Analysis 90C56, 65C35, 82C22 |
| url | https://arxiv.org/abs/2604.09789 |