Stochastic Gradient Variance Reduction by Solving a Filtering Problem

by   Xingyi Yang, et al.

Deep neural networks (DNN) are typically optimized using stochastic gradient descent (SGD). However, the estimation of the gradient using stochastic samples tends to be noisy and unreliable, resulting in large gradient variance and bad convergence. In this paper, we propose Filter Gradient Decent (FGD), an efficient stochastic optimization algorithm that makes the consistent estimation of the local gradient by solving an adaptive filtering problem with different design of filters. Our method reduces variance in stochastic gradient descent by incorporating the historical states to enhance the current estimation. It is able to correct noisy gradient direction as well as to accelerate the convergence of learning. We demonstrate the effectiveness of the proposed Filter Gradient Descent on numerical optimization and training neural networks, where it achieves superior and robust performance compared with traditional momentum-based methods. To the best of our knowledge, we are the first to provide a practical solution that integrates filtering into gradient estimation by making the analogy between gradient estimation and filtering problems in signal processing. (The code is provided in


page 1

page 5


Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization

We introduce Kalman Gradient Descent, a stochastic optimization algorith...

On the Performance of Preconditioned Stochastic Gradient Descent

This paper studies the performance of preconditioned stochastic gradient...

A unified theory of adaptive stochastic gradient descent as Bayesian filtering

There are a diverse array of schemes for adaptive stochastic gradient de...

KaFiStO: A Kalman Filtering Framework for Stochastic Optimization

Optimization is often cast as a deterministic problem, where the solutio...

Lsh-sampling Breaks the Computation Chicken-and-egg Loop in Adaptive Stochastic Gradient Estimation

Stochastic Gradient Descent or SGD is the most popular optimization algo...

RankNEAT: Outperforming Stochastic Gradient Search in Preference Learning Tasks

Stochastic gradient descent (SGD) is a premium optimization method for t...

Particle Filtering Methods for Stochastic Optimization with Application to Large-Scale Empirical Risk Minimization

There is a recent interest in developing statistical filtering methods f...