Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality

• URL: http://arxiv.org/abs/2109.08430v1
• Date: Fri, 17 Sep 2021 09:44:27 GMT
• Title: Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality
• Authors: Shuchan Wang, Photios A. Stavrou and Mikael Skoglund
• Abstract summary: We prove an HWI-type inequality making use of the infinitesimal displacement convexity of optimal transport map. We derive two Talagrand-type inequalities using the saturation of EPI that corresponds to a numerical term in our expression.
• Score: 28.676190269627828
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this paper, we study the connection between entropic optimal transport and entropy power inequality (EPI). First, we prove an HWI-type inequality making use of the infinitesimal displacement convexity of optimal transport map. Second, we derive two Talagrand-type inequalities using the saturation of EPI that corresponds to a numerical term in our expression. We evaluate for a wide variety of distributions this term whereas for Gaussian and i.i.d. Cauchy distributions this term is found in explicit form. We show that our results extend previous results of Gaussian Talagrand inequality for Sinkhorn distance to the strongly log-concave case.

Related papers

• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Taming under isoperimetry [0.0]
  In this article we propose a Langevin-based scheme calledmathbfsTULA$ to sample from distributions with growing log. We derive non-asymientKL and consequently consequently satisfy a Log-Sobolev inequality.
  arXiv  Detail & Related papers  (2023-11-15T14:44:16Z)
• Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting [64.0722630873758]
  We consider rather general and broad class of Markov chains, Ito chains, that look like Euler-Maryama discretization of some Differential Equation. We prove the bound in $W_2$-distance between the laws of our Ito chain and differential equation.
  arXiv  Detail & Related papers  (2023-10-09T18:38:56Z)
• Proof of the Gaussian maximizers conjecture for the communication capacity of noisy heterodyne measurements [0.0]
  We provide a proof for a conjecture on optimality of Gaussian encondings for the ultimate communication rate. Results generalize previous ones and show a drastic difference in the structure of the optimal encoding.
  arXiv  Detail & Related papers  (2022-06-05T09:13:43Z)
• Log-Sobolev inequality and proof of Hypothesis of the Gaussian Maximizers for the capacity of quantum noisy homodyning [0.0]
  We give proof that the information-transmission capacity of the approximate position measurement with the oscillator energy constraint is attained on Gaussian encoding. We hope that this method should work also for other models lying out of the scope of the "threshold condition" ensuring that the upper bound for the capacity as a difference between the maximum and the minimum output entropies is attainable.
  arXiv  Detail & Related papers  (2022-04-22T10:43:22Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Lifting the Convex Conjugate in Lagrangian Relaxations: A Tractable Approach for Continuous Markov Random Fields [53.31927549039624]
  We show that a piecewise discretization preserves better contrast from existing discretization problems. We apply this theory to the problem of matching two images.
  arXiv  Detail & Related papers  (2021-07-13T12:31:06Z)
• Instance-Optimal Compressed Sensing via Posterior Sampling [101.43899352984774]
  We show for Gaussian measurements and emphany prior distribution on the signal, that the posterior sampling estimator achieves near-optimal recovery guarantees. We implement the posterior sampling estimator for deep generative priors using Langevin dynamics, and empirically find that it produces accurate estimates with more diversity than MAP.
  arXiv  Detail & Related papers  (2021-06-21T22:51:56Z)
• Loss function based second-order Jensen inequality and its application to particle variational inference [112.58907653042317]
  Particle variational inference (PVI) uses an ensemble of models as an empirical approximation for the posterior distribution. PVI iteratively updates each model with a repulsion force to ensure the diversity of the optimized models. We derive a novel generalization error bound and show that it can be reduced by enhancing the diversity of models.
  arXiv  Detail & Related papers  (2021-06-09T12:13:51Z)
• Spectral clustering under degree heterogeneity: a case for the random walk Laplacian [83.79286663107845]
  This paper shows that graph spectral embedding using the random walk Laplacian produces vector representations which are completely corrected for node degree. In the special case of a degree-corrected block model, the embedding concentrates about K distinct points, representing communities.
  arXiv  Detail & Related papers  (2021-05-03T16:36:27Z)
• Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains [0.0]
  We prove a concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. We show that we can recover the convergence rate of Arcones and Gin'e who proved a concentration result for U-statistics of independent random variables and canonical kernels.
  arXiv  Detail & Related papers  (2020-11-20T15:14:34Z)
• Approximate tensorization of the relative entropy for noncommuting conditional expectations [3.4376560669160385]
  We derive a new generalisation of the strong subadditivity of the entropy to the setting of general conditional expectations onto finite-dimensional von Neumann algebras. We show the equivalence between conditional expectations arising from Petz recovery maps and those of general Davies semigroups.
  arXiv  Detail & Related papers  (2020-01-22T12:20:53Z)

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.