University of Cambridge > Talks.cam > CCIMI Seminars > Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation

Download to your calendar using vCal

  • UserDr Nicolas Flammarion
  • ClockMonday 26 November 2018, 14:00-15:00
  • HouseCMS, MR11.

If you have a question about this talk, please contact J.W.Stevens .

In this talk, 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.

This talk is part of the CCIMI Seminars series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Harrods Room, Emmanuel College Webinar & LT2, Computer Laboratory, William Gates Building. Daily Local News

Other talks

Teams Announced Spectral theory for Dirac operators with singular potentials TBC Title TBC Cambridge RNA Club - IN PERSON Toward affordable preventive healthcare
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity