一类图像复原模型的全变差收敛界
Convergence bound in total variation for an image restoration model
摘要:
我们考虑了A. Gibbs(2004),并给出了该模型定义的马尔可夫链在全变差中ε-接近平衡所需时间的上界。我们使用吉布斯的结果收敛在Wasserstein度量到达我们的结果。我们对达到平衡的时间的界与吉布斯的界相似。
英文摘要:
We consider a stochastic image restoration model proposed by A. Gibbs (2004), and give an upper bound on the time it takes for a Markov chain defined by this model to be ε- close in total variation to equilibrium. We use Gibbs' result for convergence in the Wasserstein metric to arrive at our result. Our bound for the time to equilibrium of similar order to that of Gibbs.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。