Publications
Preprints
S. A. Alghunaim, K. Yuan, ‘‘CED-EF: Compressed exact diffusion with error feedback for multi-agent learning,’’ arXiv:2608.23013, August, 2026.
S. A. Alghunaim, ‘‘Stochastic gradient tracking over time-varying networks: One-step Lyapunov analysis,’’ arXiv:2608.16271, August, 2026.
H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘DAMA: A unified accelerated approach for decentralized nonconvex minimax optimization-Part II: Convergence and performance analyses,’’ arXiv:2512.13923, December, 2025.
H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘DAMA: A unified accelerated approach for decentralized nonconvex minimax optimization-Part I: Algorithm development and results,’’ arXiv:2512.13920 , December, 2025.
H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘Communication-efficient algorithms for distributed nonconvex minimax optimization problems,’’ arXiv:2507.21901, July, 2025.
L. Guo, S. A. Alghunaim, K. Yuan, L. Condat, J. Cao, ‘‘Achieving linear speedup with ProxSkip in distributed stochastic optimization,’’ arXiv:2310.07983, Oct., 2023.
Journals and Conferences
[J] H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘Accelerated stochastic min-max optimization based on bias-corrected momentum,’’ IEEE Trans. Automatic Control (early access), 2026. [arXiv]
[C] S. A. Alghunaim, ‘‘Achieving linear speed-up for distributed inexact-ADMM,’’ Proc. IEEE ICASSP, pp. 21686-21690, Barcelona, Spain, May 2026.
[C] H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘Decentralized accelerated nonconvex minimax optimization via exact diffusion,’’ Proc. IEEE ICASSP, pp. 261-265, Barcelona, Spain, May 2026.
[J] H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘Diffusion stochastic optimization for min-max problems,’’ IEEE Trans. on Signal Processing, vol. 73, pp. 259-274, 2025. [arXiv]
[J] S. A. Alghunaim, ‘‘Local exact-diffusion for decentralized optimization and learning,’’ IEEE Trans. Automatic Control, vol. 69, no. 11, pp. 7371-7386, Nov. 2024. [arXiv]
[C] H. Cai, S. A. Alghunaim, A. H. Sayed, ‘‘Diffusion optimistic learning for min-max optimization,’’ Proc. IEEE ICASSP, pp. 5535-5539, Seoul, South Korea, April 2024.
[J] S. A. Alghunaim, K. Yuan, ‘‘An enhanced gradient-tracking bound for distributed online stochastic convex optimization,’’ Signal Processing, Volume 217, April 2024. [arXiv]
[J] K. Yuan, S. A. Alghunaim, X. Huang, ‘‘Removing data heterogeneity influence enhances network topology dependence of decentralized SGD,’’ Journal of Machine Learning Research (JMLR), vol. 24, no. 280, pp. 1–53, 2023. [arXiv]
[C] H. Yuan, S. A. Alghunaim, K. Yuan, ‘‘Achieving linear speedup with network-independent learning rates in decentralized stochastic optimization,’’ Proc. IEEE CDC, pp. 139-144, Marina Bay Sands, Singapore, December 2023.
[C] E. D. H. Nguyen, S. A. Alghunaim, K. Yuan, C. A. Uribe, ‘‘On the performance of gradient tracking with local updates,’’ Proc. IEEE CDC, pp. 4309-4313, Marina Bay Sands, Singapore, December 2023. [arXiv]
[J] S. A. Alghunaim, K. Yuan, ‘‘A unified and refined convergence analysis for non-convex decentralized learning,’’ IEEE Trans. on Signal Processing, vol. 70, pp. 3264–3279, June 2022. [arXiv]
[J] S. A. Alghunaim, Q. Lyu, M. Yan, A. H. Sayed, ‘‘Dual consensus proximal algorithm for multi-agent sharing problems,’’ IEEE Trans. on Signal Processing, vol. 69, pp. 5568-5579, September 2021.
[J] S. A. Alghunaim, E. K. Ryu, K. Yuan, A. H. Sayed, ‘‘Decentralized proximal gradient algorithms with linear convergence rates,’’ IEEE Trans. Automatic Control, vol. 66, no. 6, pp. 2787-2794, June 2021. [arXiv]
[C] S. A. Alghunaim, M. Yan, A. H. Sayed, ‘‘A multi-agent primal-dual strategy for composite optimization over distributed features,’’ in Proc. EUSIPCO 2020, pp. 2095-2099, Amsterdam, The Netherlands, January 2021. [arXiv]
[J] S. A. Alghunaim, K. Yuan, A. H. Sayed, ‘‘A proximal diffusion strategy for multi-agent optimization with sparse affine constraints,’’ IEEE Trans. Automatic Control, vol. 65, no. 11, pp. 4554-4567, November 2020. [arXiv]
[J] K. Yuan, S. A. Alghunaim, B. Ying, A. H. Sayed. ‘‘On the influence of bias-correction on distributed stochastic optimization,’’ IEEE Trans. on Signal Processing, vol. 68, 4352-4367, July 2020. [arXiv]
[J] S. A. Alghunaim, A. H. Sayed, ‘‘Linear convergence of primal-dual gradient methods and their performance in distributed optimization,’’ Automatica, Volume 117, July 2020. [arXiv]
[J] S. A. Alghunaim, A. H. Sayed, ‘‘Distributed coupled multi-agent stochastic optimization,“ IEEE Trans. Automatic Control, vol. 65, no. 1, pp. 175-190, January, 2020. [arXiv]
[C] S. A. Alghunaim, K. Yuan, A. H. Sayed, ‘‘A linearly convergent proximal gradient algorithm for decentralized optimization,’’ in Advances on Neural Information Processing Systems (NeurIPS), volume 32, Vancouver, Canada, December 2019. [arXiv]
[C] K. Yuan, S. A. Alghunaim, B. Ying, A. H. Sayed, ‘‘On the performance of exact diffusion over adaptive networks,’’ Proc. IEEE CDC, pp. 4898-4903, Nice, France, December 2019.
[C] L. Cassano, S. A. Alghunaim, A. H. Sayed, ‘‘Team policy learning for multi-agent reinforcement learning,’’ Proc. IEEE ICASSP, pp. 3062-3066, Brighton, UK, May 2019.
[C] S. A. Alghunaim, K. Yuan, A. H. Sayed, ‘‘Dual coupled diffusion for distributed optimization with affine constraints,’’ Proc. IEEE CDC, pp. 829-834, Miami Beach, FL, USA, December 2018.
[C] S. A. Alghunaim, A. H. Sayed, ‘‘Distributed coupled learning over adaptive networks,’’ Proc. IEEE ICASSP, pp. 6353-6357, Calgary, Canada, April 2018.
[C] S. A. Alghunaim, K. Yuan, A. H. Sayed, ‘‘Decentralized exact coupled optimization,’’ Proc. Allerton Conference on Communication, Control, and Computing, pp. 338-345, Allerton, IL, October 2017.
[C] J. Y. Ishihara, S. A. Alghunaim, ‘‘Diffusion LMS filter for distributed estimation of systems with stochastic state transition and observation matrices,’’ Proc. American Control Conference (ACC), pp. 5199-5204, Seattle, USA, May, 2017.
Ph.D. Thesis
S. A. Alghunaim, On the Performance and Linear Convergence of Decentralized Primal-Dual Methods, Doctoral dissertation, Electrical and Computer Engineering Department, UCLA, January 2020.