|国家预印本平台
首页|Riemannian Stochastic Gradient Method for Nested Composition Optimization

Riemannian Stochastic Gradient Method for Nested Composition Optimization

Riemannian Stochastic Gradient Method for Nested Composition Optimization

来源:Arxiv_logoArxiv
英文摘要

This work considers optimization of composition of functions in a nested form over Riemannian manifolds where each function contains an expectation. This type of problems is gaining popularity in applications such as policy evaluation in reinforcement learning or model customization in meta-learning. The standard Riemannian stochastic gradient methods for non-compositional optimization cannot be directly applied as stochastic approximation of inner functions create bias in the gradients of the outer functions. For two-level composition optimization, we present a Riemannian Stochastic Composition Gradient Descent (R-SCGD) method that finds an approximate stationary point, with expected squared Riemannian gradient smaller than $\epsilon$, in $O(\epsilon^{-2})$ calls to the stochastic gradient oracle of the outer function and stochastic function and gradient oracles of the inner function. Furthermore, we generalize the R-SCGD algorithms for problems with multi-level nested compositional structures, with the same complexity of $O(\epsilon^{-2})$ for the first-order stochastic oracle. Finally, the performance of the R-SCGD method is numerically evaluated over a policy evaluation problem in reinforcement learning.

Dewei Zhang、Sam Davanloo Tajbakhsh

计算技术、计算机技术

Dewei Zhang,Sam Davanloo Tajbakhsh.Riemannian Stochastic Gradient Method for Nested Composition Optimization[EB/OL].(2022-07-19)[2025-08-02].https://arxiv.org/abs/2207.09350.点此复制

评论