Underdamped Langevin Monte Carlo (ULMC) is an algorithm used to sample from unnormalized densities by leveraging the momentum of a particle moving in a potential well. We provide a novel analysis of ULMC, motivated by two central questions: (1) Can we obtain improved sampling guarantees beyond strong log-concavity? (2) Can we achieve acceleration for sampling? For (1), prior results for ULMC only hold under a log-Sobolev inequality together with a restrictive Hessian smoothness condition. Here, we relax these assumptions by removing the Hessian smoothness condition and by considering distributions satisfying a Poincar\'e inequality. Our analysis achieves the state of art dimension dependence, and is also flexible enough to handle weakly smooth potentials. As a byproduct, we also obtain the first KL divergence guarantees for ULMC without Hessian smoothness under strong log-concavity, which is based on a new result on the log-Sobolev constant along the underdamped Langevin diffusion. For (2), the recent breakthrough of Cao, Lu, and Wang (2020) established the first accelerated result for sampling in continuous time via PDE methods. Our discretization analysis translates their result into an algorithmic guarantee, which indeed enjoys better condition number dependence than prior works on ULMC, although we leave open the question of full acceleration in discrete time. Both (1) and (2) necessitate R\'enyi discretization bounds, which are more challenging than the typically used Wasserstein coupling arguments. We address this using a flexible discretization analysis based on Girsanov's theorem that easily extends to more general settings.
翻译:Langevin Monte Carlo (ULMC) 被封存的Langevin Monte Carlo (ULMC) 是用来利用颗粒在潜在井中移动的势头,从非正常密度中提取样本的一种算法。 我们对ULMC进行了新颖的分析,其动机是两个核心问题:(1) 我们能否在严格的日志-Concoavity之外获得改进的抽样保证?(2) 我们能否实现取样加速?(1) ULMC的先前结果仅存在于一个日志-SObolev的不平等以及一个限制性的黑森光滑状态之下。在这里,我们通过消除黑森光滑的状态和考虑满足Poincar\'e不平等的分布来放松这些假设。我们的分析实现了艺术层面依赖状态的状态,并且具有足够的灵活性来应对薄弱的光滑潜力。作为副产品,我们还获得了第一个KLL的差异保证,而没有在严格的日志-Soboleve的平稳状态下,这是基于一个新结果,在不受欢迎的兰斯文传播过程中,(2) 最近Co、L和W Wang (20) 的递解的硬化突破了对精度的精度的精度的精度结构分析, 将我们之前的常规的常规分析结果转化为的不断的不断的递化结果转化为结果。