Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problems

Molei Tao, Tomoki Ohsawa
; Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:4269-4280, 2020.

Abstract

The article considers smooth optimization of functions on Lie groups. By generalizing NAG variational principle in vector space (Wibisono et al., 2016) to general Lie groups, continuous Lie-NAG dynamics which are guaranteed to converge to local optimum are obtained. They correspond to momentum versions of gradient flow on Lie groups. A particular case of $\SO(n)$ is then studied in details, with objective functions corresponding to leading Generalized EigenValue problems: the Lie-NAG dynamics are first made explicit in coordinates, and then discretized in structure preserving fashions, resulting in optimization algorithms with faithful energy behavior (due to conformal symplecticity) and exactly remaining on the Lie group. Stochastic gradient versions are also investigated. Numerical experiments on both synthetic data and practical problem (LDA for MNIST) demonstrate the effectiveness of the proposed methods as optimization algorithms (\emph{not} as a classification method).

Cite this Paper


BibTeX
@InProceedings{pmlr-v108-tao20a, title = {Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problems}, author = {Tao, Molei and Ohsawa, Tomoki}, pages = {4269--4280}, year = {2020}, editor = {Silvia Chiappa and Roberto Calandra}, volume = {108}, series = {Proceedings of Machine Learning Research}, address = {Online}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/tao20a/tao20a.pdf}, url = {http://proceedings.mlr.press/v108/tao20a.html}, abstract = {The article considers smooth optimization of functions on Lie groups. By generalizing NAG variational principle in vector space (Wibisono et al., 2016) to general Lie groups, continuous Lie-NAG dynamics which are guaranteed to converge to local optimum are obtained. They correspond to momentum versions of gradient flow on Lie groups. A particular case of $\SO(n)$ is then studied in details, with objective functions corresponding to leading Generalized EigenValue problems: the Lie-NAG dynamics are first made explicit in coordinates, and then discretized in structure preserving fashions, resulting in optimization algorithms with faithful energy behavior (due to conformal symplecticity) and exactly remaining on the Lie group. Stochastic gradient versions are also investigated. Numerical experiments on both synthetic data and practical problem (LDA for MNIST) demonstrate the effectiveness of the proposed methods as optimization algorithms (\emph{not} as a classification method).} }
Endnote
%0 Conference Paper %T Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problems %A Molei Tao %A Tomoki Ohsawa %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-tao20a %I PMLR %J Proceedings of Machine Learning Research %P 4269--4280 %U http://proceedings.mlr.press %V 108 %W PMLR %X The article considers smooth optimization of functions on Lie groups. By generalizing NAG variational principle in vector space (Wibisono et al., 2016) to general Lie groups, continuous Lie-NAG dynamics which are guaranteed to converge to local optimum are obtained. They correspond to momentum versions of gradient flow on Lie groups. A particular case of $\SO(n)$ is then studied in details, with objective functions corresponding to leading Generalized EigenValue problems: the Lie-NAG dynamics are first made explicit in coordinates, and then discretized in structure preserving fashions, resulting in optimization algorithms with faithful energy behavior (due to conformal symplecticity) and exactly remaining on the Lie group. Stochastic gradient versions are also investigated. Numerical experiments on both synthetic data and practical problem (LDA for MNIST) demonstrate the effectiveness of the proposed methods as optimization algorithms (\emph{not} as a classification method).
APA
Tao, M. & Ohsawa, T.. (2020). Variational Optimization on Lie Groups, with Examples of Leading (Generalized) Eigenvalue Problems. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in PMLR 108:4269-4280

Related Material