Papers › GO Hessian for Expectation-Based Objectives
GO Hessian for Expectation-Based Objectives
Yulai Cong, Miaoyun Zhao, Jianqiao Li, Junya Chen, Lawrence Carin
An unbiased low-variance gradient estimator, termed GO gradient, was proposed recently for expectation-based objectives 𝔼_(qᵧ(y)) [f(y)], where the random variable (RV) 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 𝔼_(qᵧ(y)) [f(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 𝔼_(qᵧ(y)) [f(y)], with rigorous experiments conducted to verify its effectiveness and efficiency.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections