arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.01291cs.LGstat.ML
收藏

基于函数项估计的生成粒子变分推理

Generative Particle Variational Inference via Estimation of Functional Gradients

Oregon State University(俄勒冈州立大学);Horizon Robotics(Horizon Robotics(地平线机器人))

Neale Ratzlaff, Qinxun Bai, Li Fuxin, Wei Xu

摘要:

最近,基于粒子的变分推理(ParVI)方法已经获得了兴趣,因为它们可以避免变分推理中常见的任意参数假设。然而,许多ParVI方法不允许从后验任意采样,并且少数允许这样采样的方法遭受次优性。本文提出了一种从后验分布中学习近似采样的新方法。我们构造了一个神经采样器,该神经采样器是用经验采样分布和目标分布之间的KL发散的函数梯度来训练的,假设梯度位于再生核希尔伯特空间内。我们的生成ParVI(GPVI)方法保持了ParVI方法的渐近性能,同时提供了生成采样器的灵活性。通过精心构建的实验,我们表明GPVI优于以前的生成ParVI方法,如摊销SVGD,并与ParVI以及黄金标准方法(如Hamiltonian Monte Carlo)竞争,以拟合精确已知和难以处理的目标分布。

英文摘要:

Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference. However, many ParVI approaches do not allow arbitrary sampling from the posterior, and the few that do allow such sampling suffer from suboptimality. This work proposes a new method for learning to approximately sample from the posterior distribution. We construct a neural sampler that is trained with the functional gradient of the KL-divergence between the empirical sampling distribution and the target distribution, assuming the gradient resides within a reproducing kernel Hilbert space. Our generative ParVI (GPVI) approach maintains the asymptotic performance of ParVI methods while offering the flexibility of a generative sampler. Through carefully constructed experiments, we show that GPVI outperforms previous generative ParVI methods such as amortized SVGD, and is competitive with ParVI as well as gold-standard approaches like Hamiltonian Monte Carlo for fitting both exactly known and intractable target distributions.

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。

↑