A Better Baseline for Second Order Gradient Estimation in Stochastic Computation Graphs
Motivated by the need for higher order gradients in multi-agent reinforcement learning and meta-learning, this paper studies the construction of baselines for second order Monte Carlo gradient estimators in order to reduce the sample variance. Following the construction of a stochastic computation graph (SCG), the Infinitely Differentiable Monte-Carlo Estimator (DiCE) can generate correct estimates of arbitrary order gradients through differentiation. However, a baseline term that serves as a control variate for reducing variance is currently provided only for first order gradient estimation, limiting the utility of higher-order gradient estimates. To improve the sample efficiency of DiCE, we propose a new baseline term for higher order gradient estimation. This term may be easily included in the objective, and produces unbiased variance-reduced estimators under (automatic) differentiation, without affecting the estimate of the objective itself or of the first order gradient. We provide theoretical analysis and numerical evaluations of our baseline term, which demonstrate that it can dramatically reduce the variance of second order gradient estimators produced by DiCE. This computational tool can be easily used to estimate second order gradients with unprecedented efficiency wherever automatic differentiation is utilised, and has the potential to unlock applications of higher order gradients in reinforcement learning and meta-learning.
Code (0)
등록된 구현이 없습니다.
Tasks
Meta-LearningMulti-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Fed-Sophia: A Communication-Efficient Second-Order Federated Learning Algorithm
Federated learning is a machine learning approach where multiple devices collaboratively learn with the help of a parameter server by sharing only their local updates. While gradient-based optimization techniques are wid…
Federated LearningSecond-order methodsGP-FL: Model-Based Hessian Estimation for Second-Order Over-the-Air Federated Learning
Second-order methods are widely adopted to improve the convergence rate of learning algorithms. In federated learning (FL), these methods require the clients to share their local Hessian matrices with the parameter serve…
Federated LearningSecond-order methodsConjugate-Gradient-like Based Adaptive Moment Estimation Optimization Algorithm for Deep Learning
Training deep neural networks is a challenging task. In order to speed up training and enhance the performance of deep neural networks, we rectify the vanilla conjugate gradient as conjugate-gradient-like and incorporate…
AdamNX: An Adam improvement algorithm based on a novel exponential decay mechanism for the second-order moment estimate
Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to loc…
Refining Adaptive Zeroth-Order Optimization at Ease
Recently, zeroth-order (ZO) optimization plays an essential role in scenarios where gradient information is inaccessible or unaffordable, such as black-box systems and resource-constrained environments. While existing ad…
Adversarial Attack