Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space

• URL: http://arxiv.org/abs/2504.17236v1
• Date: Thu, 24 Apr 2025 04:13:56 GMT
• Title: Rate-Distortion-Perception Theory for the Quadratic Wasserstein Space
• Authors: Xiqiang Qu, Jun Chen, Lei Yu, Xiangyu Xu,
• Abstract summary: We establish a single-letter characterization of the fundamental distortion-rate-perception tradeoff with limited common randomness.<n>It is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source.
• Score: 24.826457149558834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We establish 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. Moreover, it is shown that this single-letter characterization can be explicitly evaluated for the Gaussian source. Various notions of universal representation are also clarified.

Related papers

• Gaussian Rate-Distortion-Perception Coding and Entropy-Constrained Scalar Quantization [12.575809787716771]
  This paper investigates the best known bounds on the quadratic Gaussian distortion-rate-perception function with limited common randomness. The bounds are nondegenerate in the sense that they cannot be deduced from each other via a refined version of Talagrand's transportation inequality. An improved lower bound is established when the perception measure is given by the squared Wasserstein-2 distance.
  arXiv  Detail & Related papers  (2024-09-04T02:31:53Z)
• Output-Constrained Lossy Source Coding With Application to Rate-Distortion-Perception Theory [9.464977414419332]
  The distortion-rate function of output-constrained lossy source coding with limited common randomness is analyzed. An explicit expression is obtained when both source and reconstruction distributions are Gaussian.
  arXiv  Detail & Related papers  (2024-03-21T21:51:36Z)
• Edge Wasserstein Distance Loss for Oriented Object Detection [30.63435516524413]
  We propose a novel oriented regression loss, Wasserstein Distance(EWD) loss, to alleviate the square-like problem. Specifically, for the oriented box(OBox) representation, we choose a specially-designed distribution whose probability density function is only nonzero over the edges.
  arXiv  Detail & Related papers  (2023-12-12T08:00:40Z)
• An Indirect Rate-Distortion Characterization for Semantic Sources: General Model and the Case of Gaussian Observation [83.93224401261068]
  Source model is motivated by the recent surge of interest in the semantic aspect of information. intrinsic state corresponds to the semantic feature of the source, which in general is not observable. Rate-distortion function is the semantic rate-distortion function of the source.
  arXiv  Detail & Related papers  (2022-01-29T02:14:24Z)
• A Theory of the Distortion-Perception Tradeoff in Wasserstein Space [35.25746003630763]
  lower the distortion of an estimator, the more the distribution of its outputs deviates from the distribution of the signals it attempts to estimate. This phenomenon has captured significant attention in image restoration, where it implies that fidelity to ground truth images comes at the expense of perceptual quality. We show how estimators can be constructed from the estimators at the two extremes of the perception-distortion tradeoff.
  arXiv  Detail & Related papers  (2021-07-06T11:53:36Z)
• Direct Measure Matching for Crowd Counting [59.66286603624411]
  We propose a new measure-based counting approach to regress the predicted density maps to the scattered point-annotated ground truth directly. In this paper, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
  arXiv  Detail & Related papers  (2021-07-04T06:37:33Z)
• Robust Generalised Bayesian Inference for Intractable Likelihoods [9.77823546576708]
  We consider generalised Bayesian inference with a Stein discrepancy as a loss function. This is motivated by applications in which the likelihood contains an intractable normalisation constant. We show consistency, normality and bias-robustness of the posterior, highlighting how these properties are impacted by the choice of Stein discrepancy.
  arXiv  Detail & Related papers  (2021-04-15T10:31:22Z)
• Where and What? Examining Interpretable Disentangled Representations [96.32813624341833]
  Capturing interpretable variations has long been one of the goals in disentanglement learning. Unlike the independence assumption, interpretability has rarely been exploited to encourage disentanglement in the unsupervised setting. In this paper, we examine the interpretability of disentangled representations by investigating two questions: where to be interpreted and what to be interpreted.
  arXiv  Detail & Related papers  (2021-04-07T11:22:02Z)
• Determination of the critical exponents in dissipative phase transitions: Coherent anomaly approach [51.819912248960804]
  We propose a generalization of the coherent anomaly method to extract the critical exponents of a phase transition occurring in the steady-state of an open quantum many-body system.
  arXiv  Detail & Related papers  (2021-03-12T13:16:18Z)
• Quantum particle across Grushin singularity [77.34726150561087]
  We study the phenomenon of transmission across the singularity that separates the two half-cylinders. All the local realisations of the free (Laplace-Beltrami) quantum Hamiltonian are examined as non-equivalent protocols of transmission/reflection. This allows to comprehend the distinguished status of the so-called bridging' transmission protocol previously identified in the literature.
  arXiv  Detail & Related papers  (2020-11-27T12:53:23Z)
• On Localized Discrepancy for Domain Adaptation [146.4580736832752]
  This paper studies the localized discrepancies defined on the hypothesis space after localization. Their values will be different if we exchange the two domains, thus can reveal asymmetric transfer difficulties.
  arXiv  Detail & Related papers  (2020-08-14T08:30:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.