This paper introduces an alternative approach to sampling from autoregressive models. Autoregressive models are typically sampled sequentially, according to the transition dynamics defined by the model. Instead, we propose a sampling procedure that initializes a sequence with white noise and follows a Markov chain defined by Langevin dynamics on the global log-likelihood of the sequence. This approach parallelizes the sampling process and generalizes to conditional sampling. Using an autoregressive model as a Bayesian prior, we can steer the output of a generative model using a conditional likelihood or constraints. We apply these techniques to autoregressive models in the visual and audio domains, with competitive results for audio source separation, super-resolution, and inpainting.
翻译:本文介绍了一种从自动递减模型取样的替代方法。 自动递减模型通常根据模型定义的过渡动态按顺序进行抽样。 相反,我们建议了一个抽样程序,该程序可以启动一个带有白色噪音的序列,并遵循Langevin动态根据序列的全球日志相似性界定的Markov链条。该方法将取样过程与有条件取样相平行,并笼统地概括为有条件取样。 使用一种自动递减模型之前的Bayesian模式,我们可以使用有条件的可能性或限制来引导基因变异模型的输出。 我们将这些技术应用到视觉和音频域中的自动递减模型,在音频源分离、超级分辨率和插入方面有竞争性的结果。