TU1.R5.1

Low-Rate, Low-Distortion Compression with Wasserstein Distortion

Yang Qiu, Aaron B. Wagner, Cornell University, United States
Session:
Rate-Distortion Theory 2
Track:
9: Shannon Theory
Location:
Omikron I
Presentation Time:
Tue, 9 Jul, 09:45 - 10:05
Session Chair:
Aaron Wagner, Cornell University
Abstract
Wasserstein distortion is a one-parameter family of distortion measures that was recently proposed to unify fidelity and realism constraints. After establishing continuity results for Wasserstein distortion in the extreme cases of pure fidelity and pure realism, we prove the first coding theorems for compression under Wasserstein distortion focusing on the regime in which both the rate and the distortion are small.
Session TU1.R5
TU1.R5.1: Low-Rate, Low-Distortion Compression with Wasserstein Distortion
Yang Qiu, Aaron B. Wagner, Cornell University, United States
TU1.R5.2: A Distributionally Robust Approach to Shannon Limits using the Wasserstein Distance
Vikrant Malik, Taylan Kargin, Victoria Kostina, Babak Hassibi, California Institute of Technology, United States
TU1.R5.3: A Converse Bound on the Mismatched Distortion-Rate Function
Maël Le Treust, Univ. Rennes, CNRS, Inria, IRISA UMR 6074, France; Tristan Tomala, HEC Paris, France
TU1.R5.4: Uniform Distribution on $(n-1)$-Sphere: Rate-Distortion under Squared Error Distortion
Alex Dytso, Qualcomm Flarion Technologies, United States; Martina Cardone, University of Minnesota, United States
Resources
View Manuscript