← List all talks ...

Neural Distributed Source Coding

Hyeji Kim – Assistant Professor, University of Texas at Austin

Fri, 10-Nov-2023 / 2:00pm / Packard 202

Zoom Link

https://stanford.zoom.us/j/94725897176?pwd=ZFVwSXgyZXg1Y3psMUE2OW1iUlhhZz09

Abstract

Distributed source coding (DSC) is the task of encoding an input in the absence of correlated side information that is only available to the decoder. Remarkably, Slepian and Wolf showed in 1973 that an encoder without access to the side information can asymptotically achieve the same compression rate as when the side information is available. While there is vast prior work on this topic, practical DSC has been limited to synthetic datasets and specific correlation structures. In this talk, we present a framework for lossy DSC that is agnostic to the correlation structure and can scale to high dimensions. Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational AutoEncoder (VQ-VAE) to learn the distributed encoder and decoder. We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieve state-of-the-art PSNR. This is based on joint work with Jay Whang, Alliot Nagle, Anish Acharya, and Alex Dimakis.

Bio

Hyeji Kim is an Assistant Professor in the Chandra Department of Electrical and Computer Engineering at The University of Texas at Austin. H. Kim received her Ph.D. in Electrical Engineering from Stanford University in 2016. She was a postdoctoral researcher at the University of Illinois at Urbana-Champaign from 2016 to 2018 and was a researcher at Samsung AI Research Cambridge from 2018 to 2020. Her research interests lie at the intersection of information theory and machine learning.