Two-timescale Stochastic Approximation (SA) algorithms are widely used in Reinforcement Learning (RL). Their iterates have two parts that are updated with distinct stepsizes. In this work we provideâ€¦ (More)

For successful estimation, the usual network tomography algorithms crucially require i) end-to-end data generated using multicast probe packets, real or emulated, and ii) the network to be a treeâ€¦ (More)

High dimensional unconstrained quadratic programs (UQPs) involving massive datasets are now common in application areas such as web, social networks, etc. Unless computational resources that match upâ€¦ (More)

2016 Information Theory and Applications Workshopâ€¦

2016

This is a summary of the main results of [9] concerning concentration of interpolated iterates of a Robbins-Monro scheme around the trajectory of a limiting differential equation from some time on.

We develop a stochastic approximation version of the classical Kaczmarz algorithm that is incremental in nature and takes as input noisy real time data. Our analysis shows that with probability oneâ€¦ (More)

TD(0) is one of the most commonly used algorithms in reinforcement learning. Despite this, there is no existing finite sample analysis for TD(0) with function approximation, even for the linear case.â€¦ (More)