Timezone: »

Robust Low Rank Kernel Embeddings of Multivariate Distributions
Le Song · Bo Dai

Sat Dec 07 07:00 PM -- 11:59 PM (PST) @ Harrah's Special Events Center, 2nd Floor

Kernel embedding of distributions has led to many recent advances in machine learning. However, latent and low rank structures prevalent in real world distributions have rarely been taken into account in this setting. Furthermore, no prior work in kernel embedding literature has addressed the issue of robust embedding when the latent and low rank information are misspecified. In this paper, we propose a hierarchical low rank decomposition of kernels embeddings which can exploit such low rank structures in data while being robust to model misspecification. We also illustrate with empirical evidence that the estimated low rank embeddings lead to improved performance in density estimation.

Author Information

Le Song (Georgia Institute of Technology)
Bo Dai (Google Brain)

More from the Same Authors