Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement
From MaRDI portal
Publication:2692526
DOI10.3150/22-BEJ1493MaRDI QIDQ2692526
Louis Sharrock, Nikolas Kantas
Publication date: 22 March 2023
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2007.15998
stochastic gradient descentKalman-Bucy filteronline parameter estimationoptimal sensor placementrecursive maximum likelihoodtwo-timescale stochastic approximationBeneš filter
Filtering in stochastic control theory (93E11) Estimation and detection in stochastic control theory (93E10) Stochastic approximation (62L20)
Related Items
Online parameter estimation for the McKean-Vlasov stochastic differential equation, Continuous‐time stochastic gradient descent for optimizing over the stationary distribution of stochastic differential equations
Cites Work
- Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms
- Nonconvergence to unstable points in urn models and stochastic approximations
- Fundamentals of stochastic filtering
- Convergence of continuous time stochastic ELS parameter estimation
- Stochastic approximation methods for constrained and unconstrained systems
- Approximate nonlinear filtering by projection on exponential manifolds of densities
- Recursive identification in continuous-time stochastic processes
- Parameter identification for partially observed diffusions
- On a continuous time stochastic approximation problem
- Stochastic approximation with two time scales
- Asymptotic stability, ergodicity and other asymptotic properties of the nonlinear filter.
- On Poisson equation and diffusion approximation. II.
- On the stability and the uniform propagation of chaos properties of ensemble Kalman-Bucy filters
- On the Poisson equation and diffusion approximation. I
- Convergence rate of linear two-time-scale stochastic approximation.
- Online drift estimation for jump-diffusion processes
- On the stability and the concentration of extended Kalman-Bucy filters
- Semimartingale stochastic approximation procedure and recursive estimation
- Inference in hidden Markov models.
- Parameter estimation in stochastic differential equations.
- Linear stochastic approximation driven by slowly varying Markov chains
- On the determination of optimal costly measurement strategies for linear stochastic systems
- Stochastic differential systems. I: Filtering and control. A function space approach
- Martingale Models of Stochastic Approximation and Their Convergence
- Optimal Control and Observation Locations for Time-Varying Systems on a Finite-Time Horizon
- Long-Time Stability and Accuracy of the Ensemble Kalman--Bucy Filter for Fully Observed Processes and Small Measurement Noise
- An Invariant Measure Approach to the Convergence of Stochastic Approximations with State Dependent Noise
- Des resultats de non existence de filtre de dimension finie
- Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
- Exact finite-dimensional nonlinear filters
- Connection between continuous and discrete Riccati equations with applications to kalman filtering
- Exact finite-dimensional filters for certain diffusions with nonlinear drift
- Explicit filters for diffusions with certain nonlinear drifts†
- Optimal location of process measurements
- Analysis of recursive stochastic algorithms
- The dynamic system method and the traps
- A differential geometric approach to nonlinear filtering: the projection filter
- OnActor-Critic Algorithms
- Gradient Convergence in Gradient methods with Errors
- Sensor Choice for Minimum Error Variance Estimation
- Stochastic Gradient Descent in Continuous Time
- Multilevel Stochastic Gradient Methods for Nested Composition Optimization
- Applied Stochastic Differential Equations
- A Dynamical System Approach to Stochastic Approximations
- Continuous-time stochastic approximation: Convergence and asymptotic efficiency
- Actor-Critic--Type Learning Algorithms for Markov Decision Processes
- The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
- Asymptotic Properties of Recursive Particle Maximum Likelihood Estimation
- Stochastic Gradient Descent in Continuous Time: A Central Limit Theorem
- Online Maximum-Likelihood Estimation of the Parameters of Partially Observed Diffusion Processes
- The Infinite-Dimensional Optimal Filtering Problem with Mobile and Stationary Sensor Networks
- Analyticity, Convergence, and Convergence Rate of Recursive Maximum-Likelihood Estimation in Hidden Markov Models
- On Unscented Kalman Filtering for State Estimation of Continuous-Time Nonlinear Systems
- On the Differential Equations Satisfied by Conditional Probablitity Densities of Markov Processes, with Applications
- Stochastic Partial Differential Equation Based Modelling of Large Space–Time Data Sets
- ON STATIONARY PROCESSES IN THE PLANE
- Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
