TR2026-041

ProxiCBO: A Consensus-based Method for Composite Optimization

    •  Zhang, H., Ma, Y., Kitichotkul, R., Rapp, J., Boufounos, P.T., "ProxiCBO: A Consensus-based Method for Composite Optimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2026.
      BibTeX TR2026-041 PDF
      • @inproceedings{Zhang2026may,
      • author = {Zhang, Haoyu and Ma, Yanting and Kitichotkul, Ruangrawee and Rapp, Joshua and Boufounos, Petros T.},
      • title = {{ProxiCBO: A Consensus-based Method for Composite Optimization}},
      • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
      • year = 2026,
      • month = may,
      • url = {https://www.merl.com/publications/TR2026-041}
      • }
  • MERL Contacts:
  • Research Areas:

    Computational Sensing, Data Analytics, Optimization, Signal Processing

Abstract:

This paper presents an interacting-particle optimization method for composite optimization problems. The proposed approach combines ideas from consensus-based optimization (CBO) with proximal gradient descent. We establish theoretical convergence guarantees for the continuous-time finite-particle dynamics and introduce an alternating update scheme for practical implementation. Finally, we validate the effectiveness of our method across several signal processing problems, demonstrating its advantages over proximal gradient de- scent, CBO, and their variants.