Abstract
We present convergence and error estimates of modified versions of the time-discrete consensus-based optimization (CBO) algorithm proposed in Carrillo et al. (ESAIM: Control Optim Calc Var, 2020) for general non-convex functions. In authors’ recent work (Ha et al. in Math Models Meth Appl Sci 30:2417–2444, 2020), rigorous error analysis of a modified version of the first-order consensus-based optimization algorithm proposed in Carrillo et al. (2020) was studied at the particle level without resorting to the kinetic equation via a mean-field limit. However, the error analysis for the corresponding time- discrete algorithm was not done mainly due to lack of discrete analogue of Itô’s stochastic calculus. In this paper, we provide a simple and elementary convergence and error analysis for a general time-discrete consensus-based optimization algorithm, which includes modifications of the three discrete algorithms in Carrillo et al. (2020), two of which are present in Ha et al. (2020). Our analysis provides numerical stability and convergence conditions for the three algorithms, as well as error estimates to the global minimum.
Similar content being viewed by others
References
Acebron, J.A., Bonilla, L.L., Pérez Vicente, C.J.P., Ritort, F., Spigler, R.: The Kuramoto model: a simple paradigm for synchronization phenomena. Rev. Mod. Phys. 77, 137–185 (2005)
Albi, G., Bellomo, N., Fermo, L., Ha, S.-L., Pareschi, L., Poyato, D., Soler, J.: Vehicular traffic, crowds, and swarms. On the kinetic theory approach towards research perspectives. Math. Models Methods Appl. Sci. 29, 1901–2005 (2019)
Bertsekas, D.: Convex Analysis and Optimization. Athena Scientific, Belmont (2003)
Carrillo, J.A., Jin, S., Li, L., Zhu, Y.: A consensus-based global optimization method for high dimensional machine learning problems. ESAIM: Control Optim. Calc. Var. (2020)
Carrillo, J., Choi, Y.-P., Totzeck, C., Tse, O.: An analytical framework for consensus-based global optimization method. Math. Models Methods Appl. Sci. 28, 1037–1066 (2018)
Choi, Y.-P., Ha, S.-Y., Li, Z.: Emergent dynamics of the Cucker–Smale flocking model and its variants. In: Bellomo, N., Degond, P., Tadmor, E. (eds.) Active Particles Vol. I Theory, Models, Applications (Tentative Title), Series: Modeling and Simulation in Science and Technology. Birkhauser, Springer, Berlin (2017)
Crow, E.L., Shimizu, K. (eds.): Lognormal Distributions: Theory and Applications. Statistics: Textbooks and Monographs. Marcel-Dekker Inc., New York (1988)
Cucker, F., Smale, S.: On the mathematics of emergence. Jpn. J. Math. 2, 197–227 (2007)
Dembo, A., Zeitouni, O.: Large Deviations Techniques and Applications, 2nd edn. Springer, Heidelberg, Berlin (1998)
Eberhart, R., Kennedy, J.: Particle swarm optimization. Proc. IEEE Int. Conf. Neural Netw. 4, 1942–1948 (1995)
Fang, D., Ha, S.-Y., Jin, S.: Emergent behaviors of the Cucker–Smale ensemble under attractive-repulsive couplings and Rayleigh frictions. Math. Models Methods Appl. Sci. 29, 1349–1385 (2019)
Fornasier, M., Huang, H., Pareschi, L., S\(\ddot{u}\)nnen, P.: Consensus-based optimization on the sphere I: well-posedness and mean-field limit. Preprint. Available at arXiv:2001.110994v2
Fornasier, M., Huang, H., Pareschi, L., S\(\ddot{u}\)nnen, P.: Consensus-based optimization on the sphere II: convergence to global minimizer and machine learning. Preprint. Available at arXiv:2001.11988v2
Ha, S.-Y., Jin, S., Kim, D.: Convergence of a first-order consensus-based global optimization algorithm. Math. Models Meth. Appl. Sci. 30, 2417–2444 (2020)
Ha, S.-Y., Liu, J.-G.: A simple proof of Cucker–Smale flocking dynamics and mean-field limit. Commun. Math. Sci. 7, 297–325 (2009)
Ha, S.-Y., Lee, K., Levy, D.: Emergence of time-asymptotic flocking in a stochastic Cucker–Smale system. Commun. Math. Sci. 7, 453–469 (2009)
Holland, J.H.: Genetic algorithms. Sci. Am. 267, 66–73 (1992)
Hsu, L.C.: A theorem on the asymptotic behavior of a multiple integral. Duke Math. J. 15, 623–632 (1948)
Kennedy, J.: Swarm Intelligence. Handbook of Nature-Inspired and Innovative computing, pp. 187–219. Springer, Berlin (2006)
Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220, 671–680 (1983)
Kolokolnikov, T., Carrillo, J.A., Bertozzi, A., Fetecau, R., Lewis, M.: Emergent behavior in a multi-particle systems with non-local interactions. Physica D 260, 1–4 (2013)
Kuramoto, Y.: Chemical Oscillations, Waves and Turbulence. Springer, Berlin (1984)
Kuramoto, Y.: International symposium on mathematical problems in mathematical physics. Lect. Notes Theor. Phys. 30, 420 (1975)
Motsch, S., Tadmor, E.: Heterophilious dynamics enhances consensus. SIAM. Rev. 56, 577–621 (2014)
Peskin, C.S.: Mathematical Aspects of Heart Physiology. Courant Institute of Mathematical Sciences, New York (1975)
Pinnau, R., Totzeck, C., Tse, O., Martin, S.: A consensus-based model for global optimization and its mean-field limit. Math. Models Methods Appl. Sci. 27, 183–204 (2017)
Pikovsky, A., Rosenblum, M., Kurths, J.: Synchronization: A Universal Concept in Nonlinear Sciences. Cambridge University Press, Cambridge (2001)
Totzeck, C., Pinnau, R., Blauth, S., Schotthöfer, S.: A numerical comparison of consensus-based global optimization to other particle-based global optimization scheme. Proc. Appl. Math. Mech. 18, e201800291 (2018)
van Laarhoven, P.J.M., Aarts, E.H.L.: Simulated Annealing: Theory and Applications. D. Reidel Publishing Co., Dordrecht (1987)
Vicsek, T., Zefeiris, A.: Collective motion. Phys. Rep. 517, 71–140 (2012)
Yang, X.-S.: Nature-Inspired Metaheuristic Algorithms. Luniver Press, Paris (2010)
Yang, X.-S., Deb, S., Zhao, Y.-X., Fong, S., He, X.: Swarm intelligence: past, present and future. Soft Comput. 22, 5923–5933 (2018)
Acknowledgements
The work of S.-Y. Ha was supported by National Research Foundation of Korea (NRF-2020R1A2C3A01003881), and the work of S. Jin was supported by NSFC Grant Nos. 11871297 and 3157107, and the work of D. Kim was supported by a KIAS Individual Grant (MG073901) at Korea Institute for Advanced Study. The authors would like to thank Professor Dongnam Ko for his helpful comments on the Laplace principle.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Error estimate under an alternative framework
Error estimate under an alternative framework
In this subsection, we provide an alternative result for an error estimate for time-discrete CBO scheme (1.1) without using Laplace’s principle under a slightly different framework \(({{\mathcal {B}}}1) - ({{\mathcal {B}}}2)\). Below, we present a framework for the objective function L, global minimum point \(X_*\) and reference random variable \({X_\text {in}}\) as follows:
-
\(({{\mathcal {B}}}1)\): Let \(L = L(x)\) be a \(C^2\)-objective function satisfying the following relations:
$$\begin{aligned} L_m{:}{=}\min _{x \in {\mathbb {R}}^d} L(x) >0 \quad \text{ and } \quad C_L{:}{=}\sup _{x\in {\mathbb {R}}^d}\Vert \nabla ^2L(x)\Vert _2 <\infty , \end{aligned}$$where \(\Vert \cdot \Vert _2\) denotes the spectral norm.
-
\(({{\mathcal {B}}}2)\): Let \({X_\text {in}}\) be a reference random variable associated with a law whose support \({{\tilde{D}}}\) is compact and contains \(X_*\).
Note that the condition \(({{\mathcal {B}}}1)\) is exactly the same as \(({{\mathcal {A}}}1)\), whereas the condition \(({{\mathcal {B}}}2)\) is different from \(({{\mathcal {A}}}3)\) in which the probability measures associated with \({X_\text {in}}\) is absolutely continuous with respect to Lebesgue measure. Moreover, notice that this new framework does not need any condition on \({\text {det}}\left( \nabla ^2 L(X_*)\right) \) as in \(({{\mathcal {A}}}2)\).
Next, we study how the common consensus state \(X_\infty \) is close to the global minimum \(X_*\) in suitable sense. Now, we are ready to provide an error estimate for the discrete CBO algorithm, which is analogous to Theorem 4.1 in [14] for the continuous case.
Theorem 5.1
Suppose that the framework \(({{\mathcal {B}}}1) - ({{\mathcal {B}}}2)\) holds, and parameters \(\beta , \gamma , \zeta , \delta \) and the initial data \(\{X_0^i \}\) satisfy
for some \(0<\varepsilon <1\). Then, for a solution \(\{X_n^i\}_{1\le i\le N}\) to (1.1),
Before we provide a proof, we give several comments on the result of this theorem. 1. In the proof of Theorem 5.1, we will first derive the estimate:
2. For any given \(\delta> 0,~\varepsilon > 0\) and \(\beta > 0\), the conditions (5.1) can be attained with suitable \({X_\text {in}}\). To see this, we choose the law of \({X_\text {in}}\) such that \({{\tilde{D}}}\) is a small neighborhood of a global minimum \(X_*\) satisfying the following two relations:
and
where \({{\mathcal {R}}}_{in} = [a_1, b_1] \times \cdots \times [a_d, b_d]\) is the smallest closed d-dimensional rectangle containing \({{\tilde{D}}}\) so that
for each \(\ell = 1, \ldots , d\). Then, due to (5.6), the relation (5.5) implies the condition (5.1)\(_2\). Hence, we can apply the estimate (5.3) and (5.4) to get the desired error estimate:
Now we are ready to provide a proof of Theorem 5.1. Similar to the proof of Theorem 3.2, we obtain
Hence one has
Finally, we take logarithm to the both sides of the above relation to get the desired estimate (5.3).
Rights and permissions
About this article
Cite this article
Ha, SY., Jin, S. & Kim, D. Convergence and error estimates for time-discrete consensus-based optimization algorithms. Numer. Math. 147, 255–282 (2021). https://doi.org/10.1007/s00211-021-01174-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00211-021-01174-y