[论文解读] A Stein variational Newton method

Gianluca Detommaso, Tiangang Cui+3 more|arXiv (Cornell University)|Jun 8, 2018

Markov Chains and Monte Carlo Methods参考文献 28被引用 42

一句话总结

本文在 Stein variational gradient descent 的基础上加入二阶（牛顿式）信息以改进采样器，提出带几何感知核的 Stein variational Newton (SVN) 方法，以加速收敛。

ABSTRACT

Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reproducing kernel Hilbert space. In this paper, we accelerate and generalize the SVGD algorithm by including second-order information, thereby approximating a Newton-like iteration in function space. We also show how second-order information can lead to more effective choices of kernel. We observe significant computational gains over the original SVGD algorithm in multiple test cases.

研究动机与目标

• Motivate acceleration of nonparametric variational inference for challenging target distributions
• Introduce a Newton-like iteration in function space for transport maps
• Leverage second-order information to improve kernel choice and particle movement
• Propose scalable approximations to compute Newton directions in RKHS
• Demonstrate computational gains and kernel design benefits via experiments

提出的方法

• Define a Newton-like direction in the space of transport maps to minimize a local quadratic approximation of the KL objective
• Derive a Galerkin (kernel) representation to compute the Newton direction via a finite-dimensional linear system
• Introduce inexact Newton–CG and block-diagonal Hessian approximations for scalability
• Develop geometry-aware anisotropic kernels using an average Hessian M_p to adapt distances in the RKHS
• Provide Algorithms 1 and 2 detailing SVGD and SVN iterations respectively
• Discuss scaling and kernel choices with a Hessian-based kernel normalization (g(d) factor) for high-dimensional problems

实验结果

研究问题

• RQ1 Can second-order information accelerate convergence of Stein variational methods for sampling?
• RQ2 How can one design kernels that incorporate curvature information to improve transport in high probability regions?
• RQ3 What scalable approximations (block-diagonal, inexact Newton) preserve descent while reducing computation?
• RQ4 Does a geometry-aware kernel outperform isotropic kernels in challenging Bayesian inference tasks?

主要发现

• SVN with second-order information converges faster than standard SVGD in test cases
• A geometry-aware Hessian kernel significantly improves convergence speed and particle distribution
• Block-diagonal and inexact Newton–CG approximations provide scalable alternatives with similar progress per iteration
• Scaled Hessian kernels help maintain robust performance in high-dimensional settings
• SVN-H (Newton with Hessian kernel) achieves accurate posterior means and credible intervals in high-dimensional diffusion tests
• The method shows good agreement with reference MCMC in a Langevin SDE example