Multi-kernel Passive Stochastic Gradient Algorithms

08/23/2020 ∙ by Vikram Krishnamurthy, et al. ∙ 0 ∙ share

This paper develops a novel passive stochastic gradient algorithm. In passive stochastic approximation, the stochastic gradient algorithm does not have control over the location where noisy gradients of the cost function are evaluated. Classical passive stochastic gradient algorithms use a kernel that approximates a Dirac delta to weigh the gradients based on how far they are evaluated from the desired point. In this paper we construct a multi-kernel passive stochastic gradient algorithm. The algorithm performs substantially better in high dimensional problems and incorporates variance reduction. We analyze the weak convergence of the multi-kernel algorithm and its rate of convergence. In numerical examples, we study the multi-kernel version of the LMS algorithm to compare the performance with the classical passive version.

READ FULL TEXT

Langevin Dynamics for Inverse Reinforcement Learning of Stochastic Gradient Algorithms

Inverse reinforcement learning (IRL) aims to estimate the reward functio...
06/20/2020 ∙ by Vikram Krishnamurthy, et al. ∙ 0 ∙ share

read it
Variance reduction for distributed stochastic gradient MCMC

Stochastic gradient MCMC methods, such as stochastic gradient Langevin d...
04/23/2020 ∙ by Khaoula El Mekkaoui, et al. ∙ 11 ∙ share

read it
SVAG: Unified Convergence Results for SAG-SAGA Interpolation with Stochastic Variance Adjusted Gradient Descent

We analyze SVAG, a variance reduced stochastic gradient method with SAG ...
03/21/2019 ∙ by Martin Morin, et al. ∙ 0 ∙ share

read it
A Universally Optimal Multistage Accelerated Stochastic Gradient Method

We study the problem of minimizing a strongly convex and smooth function...
01/23/2019 ∙ by Necdet Serhat Aybat, et al. ∙ 0 ∙ share

read it
Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems

Stochastic approximation (SA) algorithms have been widely applied in min...
06/23/2019 ∙ by Jingyi Zhu, et al. ∙ 0 ∙ share

read it
On the rates of convergence of Parallelized Averaged Stochastic Gradient Algorithms

The growing interest for high dimensional and functional data analysis l...
10/22/2017 ∙ by Antoine Godichon-Baggioni, et al. ∙ 0 ∙ share

read it
A fast and recursive algorithm for clustering large datasets with k-medians

Clustering with fast algorithms large samples of high dimensional data i...
01/21/2011 ∙ by Hervé Cardot, et al. ∙ 0 ∙ share

read it

Multi-kernel Passive Stochastic Gradient Algorithms

Authors

Langevin Dynamics for Inverse Reinforcement Learning of Stochastic Gradient Algorithms

Variance reduction for distributed stochastic gradient MCMC

SVAG: Unified Convergence Results for SAG-SAGA Interpolation with Stochastic Variance Adjusted Gradient Descent

A Universally Optimal Multistage Accelerated Stochastic Gradient Method

Efficient Implementation of Second-Order Stochastic Approximation Algorithms in High-Dimensional Problems

On the rates of convergence of Parallelized Averaged Stochastic Gradient Algorithms

A fast and recursive algorithm for clustering large datasets with k-medians

This week in AI