Dear All
We are delighted to announce our next Oxford Probability for Machine Learning Seminar
Thursday February 29 from 4-5 pm, online only
Speaker: Prof Larry Goldstein (University of Southern California, Los Angeles)
https://dornsife.usc.edu/larry-goldstein/
Title: Relaxing Gaussian Assumptions in High Dimensional Statistical Procedures
Abstract: The assumption that high dimensional data is Gaussian is pervasive in many statistical procedures due to the ease of analytic tractability this special distribution provides. We explore the relaxation of the Gaussian assumption in Shrinkage estimation, Stein's Unbiased Risk Estimate, and Single Index Models, using two tools that originate in Stein's method: Stein kernels, and the zero bias distribution. Taking this approach leads to measures of discrepancy from the Gaussian that arise naturally from the form of the procedures considered, and result in performance bounds that apply in contexts not restricted to the Gaussian. The resulting bounds typically include an additional term that reflects the cost of deviation from the Gaussian, and that vanishes for the Gaussian, thus recovering this particular special case. -- This is based on joint work with Xiaohan Wei, Max Fathi, Gesine Reinert, and Adrien Saumard
The zoom link for the talk will be published a day before the talk.
All welcome
Gesine
########################################################################
To unsubscribe from the APPLIEDPROB list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/WA-JISC.exe?SUBED1=APPLIEDPROB&A=1
This message was issued to members of www.jiscmail.ac.uk/APPLIEDPROB, a mailing list hosted by www.jiscmail.ac.uk, terms & conditions are available at https://www.jiscmail.ac.uk/policyandsecurity/
|