Abstract
In this paper, we propose an adaptive sampling stochastic multigradient algorithm for solving stochastic multiobjective optimization problems. Instead of requiring additional storage or computation of full gradients, the proposed method reduces variance by adaptively controlling the sample size used. Without the convexity assumption on the objective functions, we obtain that the proposed algorithm converges to Pareto stationary points in almost surely. We then analyze the convergence rates of the proposed algorithm. Numerical experiments are presented to demonstrate the effectiveness of the proposed algorithm.
Similar content being viewed by others
References
Ansary, M.A., Panda, G.: A modified quasi-Newton method for vector optimization problem. Optimization 64(11), 2289–2306 (2015)
Beiser, F., Keith, B., Urbainczyk, S., Wohlmuth, B.: Adaptive sampling strategies for risk-averse stochastic optimization with constraints. IMA J. Numer. Anal. (2023). https://doi.org/10.1093/imanum/drac083
Bollapragada, R., Byrd, R.H., Nocedal, J.: Adaptive sampling strategies for stochastic optimization. SIAM J. Optim. 28(4), 3312–3343 (2018)
Bottou, L., Curtis, F.E., Nocedal, J.: Optimization methods for large-scale machine learning. SIAM Rev. 60(2), 223–311 (2018)
Byrd, R.H., Chin, G.M., Nocedal, J., Wu, Y.: Sample size selection in optimization methods for machine learning. Math. Program. 134(1), 127–155 (2012)
Cartis, C., Scheinberg, K.: Global convergence rate analysis of unconstrained optimization methods based on probabilistic models. Math. Program. 169(2), 337–375 (2018)
Cho, J.H., Wang, Y.T., Chen, R., Chan, K.S., Swami, A.: A survey on modeling and optimizing multi-objective systems. IEEE Commun. Surv. Tutor. 19(3), 1867–1901 (2017)
Curtis, F.E., Scheinberg, K.: Adaptive stochastic optimization: a framework for analyzing stochastic optimization algorithms. IEEE Signal Proc. Mag. 37(5), 32–42 (2020)
Durrett, R.: Probability: Theory and Examples. Cambridge University Press, London (2010)
Ehrgott, M.: Multicriteria Optimization. Springer, Berlin (2005)
Eichfelder, G., Warnow, L.: An approximation algorithm for multi-objective optimization problems using a box-coverage. J. Global Optim. 83(2), 329–357 (2022)
Fliege, J., Svaiter, B.F.: Steepest descent methods for multicriteria optimization. Math. Methods Oper. Res. 51(3), 479–494 (2000)
Fliege, J., Vaz, A.I.F., Vicente, L.N.: Complexity of gradient descent for multiobjective optimization. Optim. Methods Softw. 34(5), 949–959 (2019)
Fliege, J., Werner, R.: Robust multiobjective optimization & applications in portfolio optimization. Eur. J. Oper. Res. 234(2), 422–433 (2014)
Fliege, J., Xu, H.F.: Stochastic multiobjective optimization: sample average approximation and applications. J. Optim. Theory Appl. 151(1), 135–162 (2011)
Fukuda, E.H., Graña Drummond, L.M.: A survey on multiobjective descent methods. Pesqui. Oper. 34(3), 585–620 (2014)
Garrigos, G.: Square distance functions are Polyak–Łojasiewicz and vice-versa. arXiv:2301.10332 (2023)
Garrigos, G., Rosasco, L., Villa, S.: Convergence of the forward-backward algorithm: beyond the worst-case with the help of geometry. Math. Program. 198(1), 937–996 (2023)
Goncalves, M.L.N., Lima, F.S., Prudente, L.F.: Globally convergent Newton-type methods for multiobjective optimization. Comput. Optim. Appl. 83(2), 403–434 (2022)
Gutjahr, W.J., Pichler, A.: Stochastic multi-objective optimization: a survey on non-scalarizing methods. Ann. Oper. Res. 236(2), 475–499 (2016)
Hu, Z., Shaloudegi, K., Zhang, G.J., Yu, Y.L.: Federated learning meets multi-objective optimization. IEEE Trans. Netw. Sci. Eng. 9(4), 2039–2051 (2022)
Hunter, S.R., Applegate, E.A., Arora, V., Chong, B., Cooper, K., Guevara, O.R., Valencia, C.V.: An introduction to multiobjective simulation optimization. ACM Trans. Model. Comput. Simul. 29(1), 1–36 (2019)
Jin, Y.C., Sendhoff, B.: Pareto-based multiobjective machine learning: an overview and case studies. IEEE Trans. Syst. Man Cybern. Part C 38(3), 397–415 (2008)
Karimi, H., Nutini, J., Schmidt, M.: Linear convergence of gradient and proximal-gradient methods under the Polyak-Łojasiewicz condition. In: Frasconi, P., Landwehr, N., Manco, G., Vreeken, J. (eds.), Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2016, Proceedings. Springer International Publishing, Part I 16, pp. 795–811 (2016)
Lin, G.H., Zhang, D.L., Liang, Y.C.: Stochastic multiobjective problems with complementarity constraints and applications in healthcare management. Eur. J. Oper. Res. 226(3), 461–470 (2013)
Lin, X., Zhen, H.L., Li, Z.H., Zhang, Q.F., Kwong, S.: Pareto multi-task learning. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\(^{\prime }\)Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 12037–12047 (2019)
Liu, S., Vicente, L.N.: The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learning. Ann. Oper. Res. (2021). https://doi.org/10.1007/s10479-021-04033-z
Mahdavi, M., Yang, T.B., Jin, R.: Stochastic convex optimization with multiple objectives. In: Burges, C.J., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 1115–1123 (2013)
Mercier, Q., Poirion, F., Désidéri, J.A.: A stochastic multiple gradient descent algorithm. Eur. J. Oper. Res. 271(3), 808–817 (2018)
Pasupathy, R., Glynn, P., Ghosh, S., Hashemi, F.S.: On sampling rates in simulation-based recursions. SIAM J. Optim. 28(1), 45–73 (2018)
Poirion, F., Mercier, Q., Désidéri, J.A.: Descent algorithm for nonsmooth stochastic multiobjective optimization. Comput. Optim. Appl. 68(2), 317–331 (2017)
Reiners, M., Klamroth, K., Heldmann, F., Stiglmayr, M.: Efficient and sparse neural networks by pruning weights in a multiobjective learning approach. Comput. Oper. Res. 141(5), 105676 (2022)
Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31, pp. 527–538 (2018)
Tanabe, H., Fukuda, E.H., Yamashita, N.: Convergence rates analysis of a multiobjective proximal gradient method. Optim. Lett. 17(2), 333–350 (2023)
Wiecek, M.M., Ehrgott, M., Engau, A.: Continuous multiobjective programming. In: Greco, S., Ehrgott, M., Figueira, J.R. (eds.) Multiple Criteria Decision Analysis: State of the art surveys, pp. 739–815. Springer, New York (2016)
Zhao, Y., Chen, L., Yang, X.M.: A sample average approximation method based on a gap function for stochastic multiobjective optimization problems. Pac. J. Optim. 17(6), 681–694 (2021)
Zhou, S.J., Zhang, W.P., Jiang, J.Y., Zhong, W.L., Gu, J.J., Zhu, W.W.: On the convergence of stochastic multi-objective gradient manipulation and beyond. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol. 35, pp. 38103–38115 (2022)
Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Trans. Evol. Comput. 3(4), 257–271 (1999)
Acknowledgements
The authors are grateful to the editor and two anonymous referees for their valuable comments and constructive suggestions, which have considerably enhanced the quality of the original manuscript. The first author was supported in part by the National Natural Science Foundation of China under grants 12001072 and 12271067, the China Postdoctoral Science Foundation Project under grant 2019M653332, the Chongqing Natural Science Foundation Project under grant CSTB2022NSCQ-MSX1318, the Group Building Scientific Innovation Project for universities in Chongqing under grant CXQT21021 and the open project of Key Laboratory under grant CSSXKFKTQ202006, School of Mathematical Sciences, Chongqing Normal University. The third author was supported in part by the Major Program of the National Natural Science Foundation of China under grants 11991020 and 11991024, the NSFC-RGC (Hong Kong) Joint Research Program under grant 12261160365 and the Chongqing Natural Science Foundation under grant cstc2019jcyj-zdxmX0016.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by René Henrion.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhao, Y., Chen, W. & Yang, X. Adaptive Sampling Stochastic Multigradient Algorithm for Stochastic Multiobjective Optimization. J Optim Theory Appl 200, 215–241 (2024). https://doi.org/10.1007/s10957-023-02334-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10957-023-02334-w
Keywords
- Stochastic multiobjective optimization
- Stochastic multigradient algorithm
- Adaptive sampling
- Convergence rate