GO Hessian for Expectation-Based Objectives

Yulai Cong, Miaoyun Zhao, Jianqiao Li, Junya Chen, Lawrence Carin

Research output: Contribution to journalArticlepeer-review

Abstract

An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives $\mathbb{E}_{q_{\boldsymbol{\gamma}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, where the random variable (RV) $\boldsymbol{y}$ may be drawn from a stochastic computation graph with continuous (non-reparameterizable) internal nodes and continuous/discrete leaves. Upgrading the GO gradient, we present for $\mathbb{E}_{q_{\boldsymbol{\boldsymbol{\gamma}}}(\boldsymbol{y})} [f(\boldsymbol{y})]$ an unbiased low-variance Hessian estimator, named GO Hessian. Considering practical implementation, we reveal that GO Hessian is easy-to-use with auto-differentiation and Hessian-vector products, enabling efficient cheap exploitation of curvature information over stochastic computation graphs. As representative examples, we present the GO Hessian for non-reparameterizable gamma and negative binomial RVs/nodes. Based on the GO Hessian, we design a new second-order method for $\mathbb{E}_{q_{\boldsymbol{\boldsymbol{\gamma}}}(\boldsymbol{y})} [f(\boldsymbol{y})]$, with rigorous experiments conducted to verify its effectiveness and efficiency.
Original languageEnglish (US)
JournalArxiv preprint
StatePublished - Jun 16 2020
Externally publishedYes

Keywords

  • stat.ML
  • cs.LG

Fingerprint Dive into the research topics of 'GO Hessian for Expectation-Based Objectives'. Together they form a unique fingerprint.

Cite this