Timezone: »

Stochastic Approximation for Canonical Correlation Analysis
Raman Arora · Teodor Vanislavov Marinov · Poorya Mianjy · Nati Srebro

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #52 #None
We propose novel first-order stochastic approximation algorithms for canonical correlation analysis (CCA). Algorithms presented are instances of inexact matrix stochastic gradient (MSG) and inexact matrix exponentiated gradient (MEG), and achieve $\epsilon$-suboptimality in the population objective in $\operatorname{poly}(\frac{1}{\epsilon})$ iterations. We also consider practical variants of the proposed algorithms and compare them with other methods for CCA both theoretically and empirically.

Author Information

Raman Arora (Johns Hopkins University)
Teodor Vanislavov Marinov (Johns Hopkins University)
Poorya Mianjy (Johns Hopkins University)
Nati Srebro (TTI-Chicago)

More from the Same Authors