26 citations · 37 across the 6 of their papers we have counts for
9 papers
Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise
Maxim Kaledin, Eric Moulines, Alexey Naumov +2
Linear two-timescale stochastic approximation (SA) scheme is an important class of algorithms which has become popular in reinforcement learning (RL), particularly for the policy e…
Recovery of compressively sensed ultrasound images with structured Sparse Bayesian Learning
Richard Porter, Vladislav Tadic, Alin Achim
In this paper, we consider the problem of recovering compressively sensed ultrasound images. We build on prior work, and consider a number of existing approaches that we consider t…
Stability of Optimal Filter Higher-Order Derivatives
Vladislav Z. B. Tadic, Arnaud Doucet
In many scenarios, a state-space model depends on a parameter which needs to be inferred from data. Using stochastic gradient search and the optimal filter (first-order) derivative…
Bias of Particle Approximations to Optimal Filter Derivative
Vladislav Z. B. Tadic, Arnaud Doucet
In many applications, a state-space model depends on a parameter which needs to be inferred from a data set. Quite often, it is necessary to perform the parameter inference online.…
Analyticity of Entropy Rates of Continuous-State Hidden Markov Models
Vladislav Z. B. Tadic, Arnaud Doucet
The analyticity of the entropy and relative entropy rates of continuous-state hidden Markov models is studied here. Using the analytic continuation principle and the stability prop…
Asymptotic Properties of Recursive Maximum Likelihood Estimation in Non-Linear State-Space Models
Vladislav Z. B. Tadic, Arnaud Doucet
Using stochastic gradient search and the optimal filter derivative, it is possible to perform recursive (i.e., online) maximum likelihood estimation in a non-linear state-space mod…