Distribution Regression: Computational vs. Statistical Trade-offs

Computational and Applied Mathematics Colloquium

Meeting Details

For more information about this meeting, contact Kristin Berrigan, John Harlim.

Speaker: Bharath Sriperumbudur, Penn State Statistics

Abstract: Distribution regression is a novel paradigm of regressing vector-valued response on probability measures where the probability measures are not fully observed but only through finite number (m) of samples drawn from them. This paradigm has many applications in forensics, climate sciences, speaker recognition, etc. In our work, we investigate this paradigm in a risk minimization framework involving reproducing kernel Hilbert spaces and propose a ridge regressor based on kernel mean embeddings. We investigate the computational vs. statistical tradeoff involving the training sample size (N) and the number of samples (m) drawn from each probability measure and show the minimax optimality of the regressor for certain growth behavior of m with respect of N with the growth rate being dependent on the smoothness of the true regressor


Room Reservation Information

Room Number: 114 McAllister

Date: 09/30/2019

Time: 12:20pm - 1:30pm