Conference
LOSSY COMPRESSION WITH DISTRIBUTION SHIFT AS ENTROPY CONSTRAINED OPTIMAL TRANSPORT
Abstract
We study an extension of lossy compression where the reconstruction distribution is different from the source distribution in order to account for distributional shift due to processing. We formulate this as a generalization of optimal transport with an entropy bottleneck to account for the rate constraint due to compression. We provide expressions for the tradeoff between compression rate and the achievable distortion with and without shared …
Authors
Liu H; Zhang G; Chen J; Khisti A
Publication Date
January 1, 2022
Conference proceedings
Iclr 2022 10th International Conference on Learning Representations