Abstract
We derive a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness under the squared error distortion measure and the squared Wasserstein-2 perception measure. This characterization is further shown to admit an explicit evaluation in the case of Gaussian sources. In addition, we clarify two different notions of universal representation. As a byproduct, soft-covering lemmas with respect to the Wasserstein-2 distance are established.
| Original language | English |
|---|---|
| Pages (from-to) | 8247-8261 |
| Number of pages | 15 |
| Journal | IEEE Transactions on Information Theory |
| Volume | 71 |
| Issue number | 11 |
| DOIs | |
| State | Published - 2025 |
Keywords
- Common randomness
- Gaussian source
- MMSE estimate
- Wasserstein distance
- lossy source coding
- optimal transport
- rate-distortion-perception theory
- soft-covering lemma
- squared error
- universal representation
- weak convergence
Fingerprint
Dive into the research topics of 'Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver