Loading...
preprint
Is There an Analog of Nesterov Acceleration for MCMC?
2019
In this paper, we study the problems of principal Generalized Eigenvector computation and Canonical Correlation Analysis in the stochastic setting. We propose a simple and efficient algorithm, Gen-Oja, for these problems. We prove the global convergence of our algorithm, borrowing ideas from the theory of fast-mixing Markov chains and two-time-scale stochastic approximation, showing that it achieves the optimal rate of convergence. In the process, we develop tools for understanding stochastic processes with Markovian noise which might be of independent interest.
Type
preprint
ArXiv ID
1902.00996
Authors
Ma, Yi-An
•
Chatterji, Niladri
•
Cheng, Xiang
•
•
Bartlett, Peter L.
•
Jordan, Michael I.
Publication date
2019
Peer reviewed
NON-REVIEWED
EPFL units
Available on Infoscience
December 2, 2019
Use this identifier to reference this record