University of Cambridge > Talks.cam > Statistics > Sparse CCA: Statistical and Computational Limits

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

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

ℹ️ Information

Sparse CCA: Statistical and Computational Limits

Download to your calendar using vCal

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

I will introduce the problem of sparse canonical correlation analysis (sparse CCA ). The first part of the talk will focus on the statistical side. I will argue that sparse CCA has an intrinsic difference from the well studied sparse PCA problem because of the presence of high-dimensional nuisance parameters, namely, the marginal covariance matrices. A somewhat surprising result we derived shows that the minimax rate of sparse CCA is independent of the structure of the marginal covariance matrices. The second part of the talk will focus on the computational side. A novel algorithm is proposed to achieve the minimax rate adaptively under an extra sample size condition. I will present a computational lower bound argument to show that such condition is necessary for all polynomial-time algorithms under the Planted Clique hypothesis. A novel reduction procedure is constructed in order that the lower bound is faithful to the Gaussianity of the model. A byproduct of this argument also provides a computational lower bound for sparse PCA under Gaussian spiked covariance model.

This talk is part of the Statistics series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 9132.12252125 kWh Department of Geography, Hardy Building Room 101 Seminar time is 1pm BST in Room FW 11, Willam Gates Hall. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon

Other talks

Talk TBC Online Causal Inference Seminar  Life, death, and the discovery of PDAR: the Pol II Degradation-dependent Apoptotic Response  Task performance predicts the substitution of feedforward by feedback drive in visual cortex The Magic of Magnetism Rothschild Public Lecture: The Quantum Centenary: from Order to Chaos
 

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