We propose a sampling algorithm that achieves superior complexity bounds in all the classical settings (strongly log-concave, log-concave, Logarithmic-Sobolev inequality (LSI), Poincar\'e inequality) as well as more general settings with semi-smooth or composite potentials. Our algorithm is based on the proximal sampler introduced in~\citet{lee2021structured}. The performance of this proximal sampler is determined by that of the restricted Gaussian oracle (RGO), a key step in the proximal sampler. The main contribution of this work is an inexact realization of RGO based on approximate rejection sampling. To bound the inexactness of RGO, we establish a new concentration inequality for semi-smooth functions over Gaussian distributions, extending the well-known concentration inequality for Lipschitz functions. Applying our RGO implementation to the proximal sampler, we achieve state-of-the-art complexity bounds in almost all settings. For instance, for strongly log-concave distributions, our method has complexity bound $\tilde\mathcal{O}(\kappa d^{1/2})$ without warm start, better than the minimax bound for MALA. For distributions satisfying the LSI, our bound is $\tilde \mathcal{O}(\hat \kappa d^{1/2})$ where $\hat \kappa$ is the ratio between smoothness and the LSI constant, better than all existing bounds.
翻译:我们提出一个抽样算法, 在所有古典设置中( 强烈对齐、 日对焦、 Logaratic- Sobolev 不平等 (LSI)、 Poincar\'e 不平等 ) 实现更高复杂度的精度。 我们的算法基于在 ⁇ citet{lee2021结构} 中引入的精度取样器。 这个准采样器的性能由限值标( ROGO) (RGO) 的性能决定, 这是近似采样器中的一个关键步骤。 这项工作的主要贡献是基于近似拒绝采样的 RGO 实现不透明化 。 要将 RGO 的不精确性设定为半色值或复合值。 我们的半色度函数基于在 ⁇ citet{le2021 结构中引入的精度采样器 。 将我们的RGOGO 的性执行应用到 prexcial $, 我们几乎在所有环境中都达到状态的复杂度。 例如, 强烈对 $Concoeval1\\\\\\\ listal listress listress 分配, 我们的方法是更精度 。