Abstract
Group synchronization aims to recover the group elements from their noisy pairwise measurements. It has found many applications in community detection, clock synchronization, and joint alignment problem. This paper focuses on the orthogonal group synchronization which is often used in cryo-EM and computer vision. However, it is generally NP-hard to retrieve the group elements by finding the least squares estimator. In this work, we first study the semidefinite programming (SDP) relaxation of the orthogonal group synchronization and its tightness, i.e., the SDP estimator is exactly equal to the least squares estimator. Moreover, we investigate the performance of the Burer-Monteiro factorization in solving the SDP relaxation by analyzing its corresponding optimization landscape. We provide deterministic sufficient conditions which guarantee: (i) the tightness of SDP relaxation; (ii) optimization landscape arising from the Burer-Monteiro approach is benign, i.e., the global optimum is exactly the least squares estimator and no other spurious local optima exist. Our result provides a solid theoretical justification of why the Burer-Monteiro approach is remarkably efficient and effective in solving the large-scale SDPs arising from orthogonal group synchronization. We perform numerical experiments to complement our theoretical analysis, which gives insights into future research directions.
Similar content being viewed by others
Notes
Here we are actually referring to the nonconvexity of \(-f({\varvec{S}}).\)
References
Abbe, E.: Community detection and stochastic block models: recent developments. J. Mach. Learn. Res. 18(1), 6446–6531 (2017)
Abbe, E., Bandeira, A.S., Bracher, A., Singer, A.: Decoding binary node labels from censored edge measurements: Phase transition and efficient recovery. IEEE Trans. Netw. Sci. Eng. 1(1), 10–22 (2014)
Absil, P.-A., Mahony, R., Sepulchre, R.: Optimization Algorithms on Matrix Manifolds. Princeton University Press, New Jersey (2009)
Arie-Nachimson, M., Kovalsky, S.Z., Kemelmacher-Shlizerman, I., Singer, A., Basri, R.: Global motion estimation from point matches. In: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, pp. 81–88. IEEE (2012)
Baik, J., Arous, G.B., Péché, S., et al.: Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices. Ann. Probab. 33(5), 1643–1697 (2005)
Bandeira, A.S.: Random Laplacian matrices and convex relaxations. Found. Comput. Math. 18(2), 345–379 (2018)
Bandeira, A.S., Boumal, N., Singer, A.: Tightness of the maximum likelihood semidefinite relaxation for angular synchronization. Math. Program. 163(1–2), 145–167 (2017)
Bandeira, A.S., Boumal, N., Voroninski, V.: On the low-rank approach for semidefinite programs arising in synchronization and community detection. In: Conference on Learning Theory, pp. 361–382 (2016)
Arous, G.B., Mei, S., Montanari, A., Nica, M.: The landscape of the spiked tensor model. Commun. Pure Appl. Math. 72(11), 2282–2330 (2019)
Ben-Tal, A., Nemirovski, A.: Lectures on Modern Convex Optimization: Analysis, Algorithms, and Engineering Applications. SIAM, Philadelphia (2001)
Benaych-Georges, F., Nadakuditi, R.R.: The eigenvalues and eigenvectors of finite, low rank perturbations of large random matrices. Adv. Math. 227(1), 494–521 (2011)
Boumal, N.: A Riemannian low-rank method for optimization over semidefinite matrices with block-diagonal constraints. ar**v preprint ar**v:1506.00575 (2015)
Boumal, N.: Nonconvex phase synchronization. SIAM J. Optim. 26(4), 2355–2377 (2016)
Boumal, N., Voroninski, V., Bandeira, A.: The non-convex Burer-Monteiro approach works on smooth semidefinite programs. In: Advances in Neural Information Processing Systems, pp. 2757–2765 (2016)
Boumal, N., Voroninski, V., Bandeira, A.S.: Deterministic guarantees for Burer-Monteiro factorizations of smooth semidefinite programs. Commun. Pure Appl. Math. 73(3), 581–608 (2020)
Burer, S., Monteiro, R.D.: A nonlinear programming algorithm for solving semidefinite programs via low-rank factorization. Math. Program. 95(2), 329–357 (2003)
Burer, S., Monteiro, R.D.: Local minima and convergence in low-rank semidefinite programming. Math. Program. 103(3), 427–444 (2005)
Candes, E.J., Li, X., Soltanolkotabi, M.: Phase retrieval via wirtinger flow: theory and algorithms. IEEE Trans. Inf. Theory 61(4), 1985–2007 (2015)
Candès, E.J., Romberg, J., Tao, T.: Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans. Inf. Theory 52(2), 489–509 (2006)
Capitaine, M., Donati-Martin, C., Féral, D.: The largest eigenvalues of finite rank deformation of large wigner matrices: convergence and nonuniversality of the fluctuations. Ann. Probab. 37(1), 1–47 (2009)
Chaudhury, K.N., Khoo, Y., Singer, A.: Global registration of multiple point clouds using semidefinite programming. SIAM J. Optim. 25(1), 468–501 (2015)
Chen, Y., Candès, E.J.: The projected power method: an efficient algorithm for joint alignment from pairwise differences. Commun. Pure Appl. Math. 71(8), 1648–1714 (2018)
Dellaert, F., Rosen, D.M., Wu, J., Mahony, R., Carlone, L.: Shonan rotation averaging: global optimality by surfing SO\((p)^{n}\). In: European Conference on Computer Vision, pp. 292–308. Springer, New York (2020)
Gao, B., Liu, X., Chen, X., Yuan, Y.-X.: A new first-order algorithmic framework for optimization problems with orthogonality constraints. SIAM J. Optim. 28(1), 302–332 (2018)
Ge, R., **, C., Zheng, Y.: No spurious local minima in nonconvex low rank problems: A unified geometric analysis. In: Proceedings of the 34th International Conference on Machine Learning, vol. 70, pp. 1233–1242 (2017)
Giridhar, A., Kumar, P.R.: Distributed clock synchronization over wireless networks: algorithms and analysis. In: Proceedings of the 45th IEEE Conference on Decision and Control, pp. 4915–4920. IEEE (2006)
Goemans, M.X., Williamson, D.P.: Improved approximation algorithms for maximum cut and satisfiability problems using semidefinite programming. J. ACM (JACM) 42(6), 1115–1145 (1995)
Huang, Q.-X., Guibas, L.: Consistent shape maps via semidefinite programming. Comput. Graph. Forum 32(5), 177–186 (2013)
Iwen, M.A., Preskitt, B., Saab, R., Viswanathan, A.: Phase retrieval from local measurements: improved robustness via eigenvector-based angular synchronization. Appl. Comput. Harmon. Anal. 48(1), 415–444 (2020)
Jung, J.H., Chung, H.W., Lee, J.O.: Weak detection in the spiked wigner model with general rank. ar**v preprint ar**v:2001.05676 (2020)
Keshavan, R.H., Montanari, A., Oh, S.: Matrix completion from a few entries. IEEE Trans. Inf. Theory 56(6), 2980–2998 (2010)
Lerman, G., Shi, Y.: Robust group synchronization via cycle-edge message passing. Found. Comput. Math. (2021)
Ling, S.: Generalized power method for generalized orthogonal Procrustes problem: global convergence and optimization landscape analysis. ar**v preprint ar**v:2106.15493 (2021)
Ling, S.: Improved performance guarantees for orthogonal group synchronization via generalized power method. SIAM J. Optim 32(2), 1018–1048 (2022). https://doi.org/10.1137/20M1389571
Ling, S.: Near-optimal performance bounds for orthogonal and permutation group synchronization via spectral methods. Appl. Comput. Harmon. Anal. 60, 20–52 (2022)
Ling, S., Xu, R., Bandeira, A.S.: On the landscape of synchronization networks: a perspective from nonconvex optimization. SIAM J. Optim. 29(3), 1879–1907 (2019)
Liu, H., Yue, M.-C., So, A.M.-C.: On the estimation performance and convergence rate of the generalized power method for phase synchronization. SIAM J. Optim. 27(4), 2426–2446 (2017)
Liu, H., Yue, M.-C., So, A.M.-C.: A unified approach to synchronization problems over subgroups of the orthogonal group. ar**v preprint ar**v:2009.07514 (2020)
Markdahl, J., Thunberg, J., Goncalves, J.: Almost global consensus on the \( n \)-sphere. IEEE Trans. Autom. Control 63(6), 1664–1675 (2017)
Markdahl, J., Thunberg, J., Goncalves, J.: High-dimensional Kuramoto models on Stiefel manifolds synchronize complex networks almost globally. Automatica 113, 108736 (2020)
Mei, S., Misiakiewicz, T., Montanari, A., Oliveira, R.I.: Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality. In: Conference on Learning Theory, pp. 1476–1515 (2017)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course, vol. 87. Springer, New York (2013)
Pachauri, D., Kondor, R., Singh, V.: Solving the multi-way matching problem by permutation synchronization. In: Advances in Neural Information Processing Systems, pp. 1860–1868 (2013)
Pataki, G.: On the rank of extreme matrices in semidefinite programs and the multiplicity of optimal eigenvalues. Math. Oper. Res. 23(2), 339–358 (1998)
Perry, A., Wein, A.S., Bandeira, A.S., Moitra, A.: Optimality and sub-optimality of PCA I: spiked random matrix models. Ann. Stat. 46(5), 2416–2451 (2018)
Recht, B., Fazel, M., Parrilo, P.A.: Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization. SIAM Rev. 52(3), 471–501 (2010)
Rosen, D.M., Carlone, L., Bandeira, A.S., Leonard, J.J.: Se-sync: a certifiably correct algorithm for synchronization over the special Euclidean group. Int. J. Robot. Res. 38(2–3), 95–125 (2019)
Singer, A.: Angular synchronization by eigenvectors and semidefinite programming. Appl. Comput. Harmon. Anal. 30(1), 20–36 (2011)
Singer, A., et al.: Mathematics for cryo-electron microscopy. Proc. Int. Congr. Math. (ICM) 3, 3981–4000 (2018)
Singer, A., Shkolnisky, Y.: Three-dimensional structure determination from common lines in cryo-em by eigenvectors and semidefinite programming. SIAM J. Imaging Sci. 4(2), 543–572 (2011)
Sun, D., Toh, K.-C., Yuan, Y., Zhao, X.-Y.: SDPNAL+: a Matlab software for semidefinite programming with bound constraints (version 1.0). Optim. Methods Softw. 35(1), 87–115 (2020)
Sun, J., Qu, Q., Wright, J.: Complete dictionary recovery over the sphere i: overview and the geometric picture. IEEE Trans. Inf. Theory 63(2), 853–884 (2016)
Sun, J., Qu, Q., Wright, J.: A geometric analysis of phase retrieval. Found. Comput. Math. 18(5), 1131–1198 (2018)
Tütüncü, R.H., Toh, K.-C., Todd, M.J.: Solving semidefinite-quadratic-linear programs using SDPT3. Math. Program. 95(2), 189–217 (2003)
Vershynin, R.: High-Dimensional Probability: An Introduction with Applications in Data Science, vol. 47. Cambridge University Press, Cambridge (2018)
Waldspurger, I., Waters, A.: Rank optimality for the Burer-Monteiro factorization. SIAM J. Optim. 30(3), 2577–2602 (2020)
Wang, L., Singer, A.: Exact and stable recovery of rotations for robust synchronization. Inf. Inference J. IMA 2(2), 145–193 (2013)
Wen, Z., Yin, W.: A feasible method for optimization with orthogonality constraints. Math. Program. 142(1–2), 397–434 (2013)
Xu, R.: On the Landscape of phase synchronization. Master’s Thesis. New York University (2019)
Yang, L., Sun, D., Toh, K.-C.: SDPNAL+: a majorized semismooth Newton-CG augmented Lagrangian method for semidefinite programming with nonnegative constraints. Math. Program. Comput. 7(3), 331–366 (2015)
Yurtsever, A., Tropp, J.A., Fercoq, O., Udell, M., Cevher, V.: Scalable semidefinite programming. SIAM J. Math. Data Sci. 3(1), 171–200 (2021)
Zhang, T.: Tightness of the semidefinite relaxation for orthogonal trace-sum maximization. ar**v preprint ar**v:1911.08700 (2019)
Zhong, Y., Boumal, N.: Near-optimal bounds for phase synchronization. SIAM J. Optim. 28(2), 989–1016 (2018)
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.
This work is (partially) financially supported by the National Key R &D Program of China, Project Number 2021YFA1002800, National Natural Science Foundation of China (NSFC) No.12001372, Shanghai Municipal Education Commission (SMEC) via Grant 0920000112, and NYU Shanghai Boost Fund.
Rights and permissions
Springer Nature or its licensor 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
Ling, S. Solving orthogonal group synchronization via convex and low-rank optimization: tightness and landscape analysis. Math. Program. 200, 589–628 (2023). https://doi.org/10.1007/s10107-022-01896-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10107-022-01896-3
Keywords
- Orthogonal group synchronization
- Convex optimization
- Low-rank optimization
- Burer-Monteiro factorization
- Optimization landscape