A Stein variational Newton method

06/08/2018
by   Gianluca Detommaso, et al.
0

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.

READ FULL TEXT

page 7

page 11

research
08/16/2016

Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm

We propose a general purpose variational inference algorithm that forms ...
research
04/19/2022

A stochastic Stein Variational Newton method

Stein variational gradient descent (SVGD) is a general-purpose optimizat...
research
03/30/2017

Diving into the shallows: a computational perspective on large-scale shallow learning

In this paper we first identify a basic limitation in gradient descent-b...
research
06/18/2020

When Does Preconditioning Help or Hurt Generalization?

While second order optimizers such as natural gradient descent (NGD) oft...
research
11/13/2017

Analyzing and Improving Stein Variational Gradient Descent for High-dimensional Marginal Inference

Stein variational gradient descent (SVGD) is a nonparametric inference m...
research
12/02/2019

On the geometry of Stein variational gradient descent

Bayesian inference problems require sampling or approximating high-dimen...
research
11/15/2017

Variational Adaptive-Newton Method for Explorative Learning

We present the Variational Adaptive Newton (VAN) method which is a black...

Please sign up or login with your details

Forgot password? Click here to reset