A neural network based policy iteration algorithm with global $H^2$-superlinear convergence for stochastic games on domains

no code implementations • 5 Jun 2019 • Kazufumi Ito, Christoph Reisinger, Yufei Zhang

In this work, we propose a class of numerical schemes for solving semilinear Hamilton-Jacobi-Bellman-Isaacs (HJBI) boundary value problems which arise naturally from exit time problems of diffusion processes with controlled drift.

Variational Gaussian Approximation for Poisson Data

no code implementations • 18 Sep 2017 • Simon Arridge, Kazufumi Ito, Bangti Jin, Chen Zhang

In this work, we analyze a variational Gaussian approximation to the posterior distribution arising from the Poisson model with a Gaussian prior.

A convex analysis approach to optimal controls with switching structure for partial differential equations

1 code implementation • 24 Feb 2017 • Christian Clason, Kazufumi Ito, Karl Kunisch

Optimal control problems involving hybrid binary-continuous control costs are challenging due to their lack of convexity and weak lower semicontinuity.

Optimization and Control