Fri, 3-Nov-2023 / 2:00pm / Packard 202
https://stanford.zoom.us/j/94725897176?pwd=ZFVwSXgyZXg1Y3psMUE2OW1iUlhhZz09
The rate-distortion function R(D) occupies a central place in the theory of lossy compression, and characterizes the fundamental compressibility of a given data source of interest. Here, I consider the problem of estimating R(D) from data samples. Starting with the classic Blahut–Arimoto algorithm, I develop new methods for estimating R(D) that can scale to high-dimensional real-world datasets such as images and speech data. I discuss the fundamental connections to statistical estimation and optimal transport behind this work, which give us new insight into the solution of the rate-distortion problem. The talk is based on the following papers: https://arxiv.org/abs/2111.12166 and https://arxiv.org/abs/2310.18908.
Yibo Yang is a fifth-year PhD student in computer science at UC Irvine advised by Stephan Mandt. He is broadly interested in applications of probability, statistics, and information theory to challenging real-world problems. His PhD research has focused on the theory and practice of lossy data compression with machine learning.
Packard Building
Electrical Engineering Department
350 Jane Stanford Way
Stanford, CA 94305-9515
