Abstract
In recent years, although the Alternating Direction Method of Multipliers (ADMM) has been empirically applied widely to many multi-convex applications, delivering an impressive performance in areas such as nonnegative matrix factorization and sparse dictionary learning, there remains a dearth of generic work on proposed ADMM with a convergence guarantee under mild conditions. In this paper, we propose a generic ADMM framework with multiple coupled variables in both objective and constraints. Convergence to a Nash point is proven with a sublinear convergence rate o(1/k). Two important applications are discussed as special cases under our proposed ADMM framework. Extensive experiments on ten real-world datasets demonstrate the proposed framework’s effectiveness, scalability, and convergence properties. We have released our code at https://github.com/xianggebenben/miADMM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The supplementary materials are available at https://github.com/xianggebenben/miADMM/blob/main/multi_convex_ADMM-13-18.pdf.
References
Ando, R.K., Zhang, T.: A framework for learning predictive structures from multiple tasks and unlabeled data. J. Mach. Learn. Res. 6, 1817–1853 (2005)
Argyriou, A., Evgeniou, T., Pontil, M.: Multi-task feature learning. In: Advances in Neural Information Processing Systems, pp. 41–48 (2007)
Bai, J., Li, J., Xu, F., Zhang, H.: Generalized symmetric ADMM for separable convex optimization. Comput. Optim. Appl. 70(1), 129–170 (2017). https://doi.org/10.1007/s10589-017-9971-0
Boţ, R.I., Nguyen, D.-K.: The proximal alternating direction method of multipliers in the nonconvex setting: convergence analysis and rates. Math. Oper. Res. 45(2), 682–712 (2020)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations Trends® Mach. Learn. 3(1), 1–122 (2011)
Carrington, P.J., Scott, J., Wasserman, S.: Models and Methods in Social Network Analysis, vol. 28. Cambridge University Press, Cambridge (2005)
Cavalletti, F., Rajala, T.: Tangent lines and Lipschitz differentiability spaces. Anal. Geom. Metr. Spaces 4(1), 85–103 (2016)
Chao, M.T., Zhang, Y., Jian, J.B.: An inertial proximal alternating direction method of multipliers for nonconvex optimization. Int. J. Comput. Math. 98(6), 1199–1217 (2021)
Chartrand, R., Wohlberg, B.: A nonconvex ADMM algorithm for group sparsity with sparse groups. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6009–6013 (2013)
Chen, J., Zhou, J., Ye, J.: Integrating low-rank and group-sparse structures for robust multi-task learning. In: Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 42–50 (2011)
Deng, W., Lai, M.-J., Peng, Z., Yin, W.: Parallel multi-block ADMM with o (1/k) convergence. J. Sci. Comput. 71(2), 712–736 (2017)
Gao, W., Goldfarb, D., Curtis, F.E.: ADMM for multiaffine constrained optimization. Optim. Methods Softw. 35(2), 257–303 (2020)
Goldstein, T., O’Donoghue, B., Setzer, S., Baraniuk, R.: Fast alternating direction optimization methods. SIAM J. Imag. Sci. 7(3), 1588–1623 (2014)
Gu, Y., Jiang, B., Han, D.: A semi-proximal-based strictly contractive Peaceman-Rachford splitting method. arXiv preprint arXiv:1506.02221, pp. 1–20 (2015)
Hassibi, A., How, J., Boyd, S.: A path-following method for solving BMI problems in control. In: Proceedings of the 1999 American Control Conference, vol. 2, pp. 1385–1389 (1999)
He, B., Yuan, X.: On the o(1/n) convergence rate of the Douglas-Rachford alternating direction method. SIAM J. Numer. Anal. 50(2), 700–709 (2012)
Kadkhodaie, M., Christakopoulou, K., Sanjabi, M., Banerjee, A.: Accelerated alternating direction method of multipliers. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 497–506 (2015)
Lee, D.D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Advances in Neural Information Processing Systems, pp. 556–562 (2001)
Li, G., Pong, T.K.: Global convergence of splitting methods for nonconvex composite optimization. SIAM J. Optim. 25(4), 2434–2460 (2015)
Li, Y., Tian, X., Liu, T., Tao, D.: Multi-task model and feature joint learning. In: International Joint Conference on Artificial Intelligence, pp. 3643–3649 (2015)
Lin, T.-Y., Ma, S.-Q., Zhang, S.-Z.: On the sublinear convergence rate of multi-block ADMM. J. Oper. Res. Soc. China 3(3), 251–274 (2015)
Ouyang, H., He, N., Tran, L., Gray, A.: Stochastic alternating direction method of multipliers. In: International Conference on Machine Learning, pp. 80–88 (2013)
Reed, T.: Open source indicators project (2017). https://doi.org/10.7910/DVN/EN8FUW
Shen, X., Diamond, S., Udell, M., Gu, Y., Boyd, S.: Disciplined multi-convex programming. In: 2017 29th Chinese Control and Decision Conference (CCDC), pp. 895–900 (2017)
Tao, M., Yuan, X.: Convergence analysis of the direct extension of ADMM for multiple-block separable convex minimization. Adv. Comput. Math. 44(3), 773–813 (2017). https://doi.org/10.1007/s10444-017-9560-x
Tseng, P.: Dual coordinate ascent methods for non-strictly convex minimization. Math. Program. 59(1–3), 231–247 (1993)
Tseng, P.: Convergence of a block coordinate descent method for nondifferentiable minimization. J. Optim. Theory Appl. 109(3), 475–494 (2001)
Wang, H., Banerjee, A.: Bregman alternating direction method of multipliers. In: Advances in Neural Information Processing Systems, pp. 2816–2824 (2014)
Wang, J., Chai, Z., Cheng, Y., Zhao, L.: Toward model parallelism for deep neural network based on gradient-free ADMM framework. In: 2020 IEEE International Conference on Data Mining (ICDM), pp. 591–600 (2020)
Wang, J., Gao, Y., Züfle, A., Yang, J., Zhao, L.: Incomplete label uncertainty estimation for petition victory prediction with dynamic features. In: 2018 IEEE International Conference on Data Mining (ICDM), pp. 537–546 (2018)
Wang, J., Li, H., Chai, Z., Wang, Y., Cheng, Y., Zhao, L.: Towards quantized model parallelism for graph-augmented MLPS based on gradient-free ADMM framework. arXiv preprint arXiv:2105.09837 (2021)
Wang, J., Yu, F., Chen, X., Zhao, L.: ADMM for efficient deep learning with global convergence. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 111–119 (2019)
Wang, J., Zhao, L.: Nonconvex generalization of alternating direction method of multipliers for nonlinear equality constrained problems. In: Results in Control and Optimization, p. 100009 (2019)
Wang, L., Li, Y., Zhou, J., Zhu, D., Ye, J.: Multi-task survival analysis. In: 2017 IEEE International Conference on Data Mining (ICDM), pp. 485–494 (2017)
Wang, Yu., Yin, W., Zeng, J.: Global convergence of ADMM in nonconvex nonsmooth optimization. J. Sci. Comput. 78(1), 29–63 (2019)
Warga, J.: Minimizing certain convex functions. J. Soc. Ind. Appl. Math. 11(3), 588–593 (1963)
Yangyang, X., Yin, W.: A block coordinate descent method for regularized multiconvex optimization with applications to nonnegative tensor factorization and completion. SIAM J. Imag. Sci. 6(3), 1758–1789 (2013)
Xu, Z., De, S., Figueiredo, M., Studer, C., Goldstein, T.: An empirical study of ADMM for nonconvex problems. In: NIPS 2016 Workshop on Nonconvex Optimization for Machine Learning: Theory and Practice (2016)
Zhao, L., Wang, J., Guo, X.: Distant-supervision of heterogeneous multitask learning for social event forecasting with multilingual indicators. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32(1), April 2018
Zhou, J., Chen, J., Ye, J.: Clustered multi-task learning via alternating structure optimization. In: Advances in Neural Information Processing Systems, pp. 702–710 (2011)
Zhou, J., Chen, J., Ye, J.: MALSAR: multi-task learning via structural regularization. Arizona State University, vol. 21 (2011)
Acknowledgement
This work was supported by the National Science Foundation (NSF) Grant No. 1755850, No. 1841520, No. 2007716, No. 2007976, No. 1942594, No. 1907805, a Jeffress Memorial Trust Award, Amazon Research Award, NVIDIA GPU Grant, and Design Knowledge Company (subcontract No: 10827.002.120.04).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, J., Zhao, L. (2022). Convergence and Applications of ADMM on the Multi-convex Problems. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13281. Springer, Cham. https://doi.org/10.1007/978-3-031-05936-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-05936-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05935-3
Online ISBN: 978-3-031-05936-0
eBook Packages: Computer ScienceComputer Science (R0)