On Learning Distributions from their Samples
published: Aug. 20, 2015, recorded: July 2015, views: 93
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
One of the most natural and important questions in statistical learning is how well a distribution can be approximated from its samples. Surprisingly, this question has so far been resolved for only a few approximation measures, for example the KL-divergence, and even then the answer is ad hoc and not well understood. We resolve the question for three more important approximation measures, $\ell_1$, $\ell_2^2$, and $\chi^2$, and if the probabilities are bounded away from zero, we resolve the question for all smooth $f$-divergence approximation measures, thereby providing a coherent understanding of the rate at which a distribution can be approximated from its samples.
Download slides: colt2015_kamath_learning_distributions_01.pdf (2.9 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !