left-arrowleft-arrowright-arrowleft-arrowAsset 9
'
Loading Events

« All Events

  • This event has passed.

Kernel approaches in global statistical distances, local measure detection, and active learning

February 5, 2020 @ 4:15 pm - 5:15 pm

In this talk, we’ll discuss the problem of constructing meaningful distances between probability distributions given only finite samples from each distribution.  We approach this through the use of data-adaptive and localized kernels, and in a variety of contexts.  First, we construct locally adaptive kernels to define fast pairwise distances between distributions, with applications to unsupervised clustering.  Then, we construct localized kernels to determine a statistical framework for determining where two distributions differ, with applications to measure detection for generative models.  Finally, we’ll begin to address the question of measure detection without a priori known labels of which distribution a point came from.  This is addressed through active learning, in which one can choose a small number of points at which to query a label.  This is ongoing work with Xiuyuan Cheng (Duke) and Hrushikesh Mhaskar (CGU), among others.

Details

Date:
February 5, 2020
Time:
4:15 pm - 5:15 pm
Event Category: