David Sprott Distinguished Lecture by Martin Wainwright, University of California, Berkeley

Thursday, May 12, 2016 4:00 pm - 4:00 pm EDT (GMT -04:00)

Some new phenomena in high-dimensional statistics and optimization

Statistical models in which the ambient dimension is of the same order
or larger than the sample size arise frequently in different areas of
science and engineering.  Examples include sparse regression in
genomics; graph selection in social network analysis; and low-rank
matrix estimation in video segmentation.  Although high-dimensional
models of this type date back to seminal work of Kolmogorov and
others, they have been the subject of especially intensive study over
the past decade, and have interesting connections to many branches of
applied mathematics and computer science, including random matrices
and algorithms, concentration of measure, convex geometry, and
information theory.  In this talk, we discuss various issues in
high-dimensional statistics, including vignettes on phase transitions
in high-dimensional graph recovery, and randomized sketching for
large-scale optimization.