11 papers
Kinetic Langevin Splitting Schemes for Constrained Sampling
Neil K. Chada, Lu Yu
Constrained sampling is an important and challenging task in computational statistics, concerned with generating samples from a distribution under certain constraints. There are nu…
Unbiased Approximations for Stationary Distributions of McKean-Vlasov SDEs
Elsiddig Awadelkarim, Neil K. Chada, Ajay Jasra
We consider the development of unbiased estimators, to approximate the stationary distribution of Mckean-Vlasov stochastic differential equations (MVSDEs). These are an important c…
Unbiased Kinetic Langevin Monte Carlo with Inexact Gradients
Neil K. Chada, Benedict Leimkuhler, Daniel Paulin +1
We present an unbiased method for Bayesian posterior means based on kinetic Langevin dynamics that combines advanced splitting methods with enhanced gradient approximations. Our ap…
The Stochastic Steepest Descent Method for Robust Optimization in Banach Spaces
Neil K. Chada, Philip J. Herbert
Stochastic gradient methods have been a popular and powerful choice of optimization methods, aimed at minimizing functions. Their advantage lies in the fact that that one approxima…
Learning dynamical systems from data: Gradient-based dictionary optimization
Mohammad Tabish, Neil K. Chada, Stefan Klus
The Koopman operator plays a crucial role in analyzing the global behavior of dynamical systems. Existing data-driven methods for approximating the Koopman operator or discovering…
Bayesian Deep Learning with Multilevel Trace-class Neural Networks
Neil K. Chada, Ajay Jasra, Kody J. H. Law +1
In this article we consider Bayesian inference associated to deep neural networks (DNNs) and in particular, trace-class neural network (TNN) priors which can be preferable to tradi…