Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis

Rong Ge, Chi Jin,  Sham, Praneeth Netrapalli, Aaron Sidford
Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:2741-2750, 2016.

Abstract

This paper considers the problem of canonical-correlation analysis (CCA) and, more broadly, the generalized eigenvector problem for a pair of symmetric matrices. These are two fundamental problems in data analysis and scientific computing with numerous applications in machine learning and statistics. We provide simple iterative algorithms, with improved runtimes, for solving these problems that are globally linearly convergent with moderate dependencies on the condition numbers and eigenvalue gaps of the matrices involved. We obtain our results by reducing CCA to the top-k generalized eigenvector problem. We solve this problem through a general framework that simply requires black box access to an approximate linear system solver. Instantiating this framework with accelerated gradient descent we obtain a running time of \order\fracz k \sqrtκρ \log(1/ε) \log \left(kκ/ρ\right) where z is the total number of nonzero entries, κis the condition number and ρis the relative eigenvalue gap of the appropriate matrices. Our algorithm is linear in the input size and the number of components k up to a \log(k) factor. This is essential for handling large-scale matrices that appear in practice. To the best of our knowledge this is the first such algorithm with global linear convergence. We hope that our results prompt further research and ultimately improve the practical running time for performing these important data analysis procedures on large data sets.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-geb16, title = {Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis}, author = {Ge, Rong and Jin, Chi and Sham, and Netrapalli, Praneeth and Sidford, Aaron}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {2741--2750}, year = {2016}, editor = {Balcan, Maria Florina and Weinberger, Kilian Q.}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/geb16.pdf}, url = {https://proceedings.mlr.press/v48/geb16.html}, abstract = {This paper considers the problem of canonical-correlation analysis (CCA) and, more broadly, the generalized eigenvector problem for a pair of symmetric matrices. These are two fundamental problems in data analysis and scientific computing with numerous applications in machine learning and statistics. We provide simple iterative algorithms, with improved runtimes, for solving these problems that are globally linearly convergent with moderate dependencies on the condition numbers and eigenvalue gaps of the matrices involved. We obtain our results by reducing CCA to the top-k generalized eigenvector problem. We solve this problem through a general framework that simply requires black box access to an approximate linear system solver. Instantiating this framework with accelerated gradient descent we obtain a running time of \order\fracz k \sqrtκρ \log(1/ε) \log \left(kκ/ρ\right) where z is the total number of nonzero entries, κis the condition number and ρis the relative eigenvalue gap of the appropriate matrices. Our algorithm is linear in the input size and the number of components k up to a \log(k) factor. This is essential for handling large-scale matrices that appear in practice. To the best of our knowledge this is the first such algorithm with global linear convergence. We hope that our results prompt further research and ultimately improve the practical running time for performing these important data analysis procedures on large data sets.} }
Endnote
%0 Conference Paper %T Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis %A Rong Ge %A Chi Jin %A Sham %A Praneeth Netrapalli %A Aaron Sidford %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-geb16 %I PMLR %P 2741--2750 %U https://proceedings.mlr.press/v48/geb16.html %V 48 %X This paper considers the problem of canonical-correlation analysis (CCA) and, more broadly, the generalized eigenvector problem for a pair of symmetric matrices. These are two fundamental problems in data analysis and scientific computing with numerous applications in machine learning and statistics. We provide simple iterative algorithms, with improved runtimes, for solving these problems that are globally linearly convergent with moderate dependencies on the condition numbers and eigenvalue gaps of the matrices involved. We obtain our results by reducing CCA to the top-k generalized eigenvector problem. We solve this problem through a general framework that simply requires black box access to an approximate linear system solver. Instantiating this framework with accelerated gradient descent we obtain a running time of \order\fracz k \sqrtκρ \log(1/ε) \log \left(kκ/ρ\right) where z is the total number of nonzero entries, κis the condition number and ρis the relative eigenvalue gap of the appropriate matrices. Our algorithm is linear in the input size and the number of components k up to a \log(k) factor. This is essential for handling large-scale matrices that appear in practice. To the best of our knowledge this is the first such algorithm with global linear convergence. We hope that our results prompt further research and ultimately improve the practical running time for performing these important data analysis procedures on large data sets.
RIS
TY - CPAPER TI - Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis AU - Rong Ge AU - Chi Jin AU - Sham AU - Praneeth Netrapalli AU - Aaron Sidford BT - Proceedings of The 33rd International Conference on Machine Learning DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-geb16 PB - PMLR DP - Proceedings of Machine Learning Research VL - 48 SP - 2741 EP - 2750 L1 - http://proceedings.mlr.press/v48/geb16.pdf UR - https://proceedings.mlr.press/v48/geb16.html AB - This paper considers the problem of canonical-correlation analysis (CCA) and, more broadly, the generalized eigenvector problem for a pair of symmetric matrices. These are two fundamental problems in data analysis and scientific computing with numerous applications in machine learning and statistics. We provide simple iterative algorithms, with improved runtimes, for solving these problems that are globally linearly convergent with moderate dependencies on the condition numbers and eigenvalue gaps of the matrices involved. We obtain our results by reducing CCA to the top-k generalized eigenvector problem. We solve this problem through a general framework that simply requires black box access to an approximate linear system solver. Instantiating this framework with accelerated gradient descent we obtain a running time of \order\fracz k \sqrtκρ \log(1/ε) \log \left(kκ/ρ\right) where z is the total number of nonzero entries, κis the condition number and ρis the relative eigenvalue gap of the appropriate matrices. Our algorithm is linear in the input size and the number of components k up to a \log(k) factor. This is essential for handling large-scale matrices that appear in practice. To the best of our knowledge this is the first such algorithm with global linear convergence. We hope that our results prompt further research and ultimately improve the practical running time for performing these important data analysis procedures on large data sets. ER -
APA
Ge, R., Jin, C., Sham, , Netrapalli, P. & Sidford, A.. (2016). Efficient Algorithms for Large-scale Generalized Eigenvector Computation and Canonical Correlation Analysis. Proceedings of The 33rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 48:2741-2750 Available from https://proceedings.mlr.press/v48/geb16.html.

Related Material