This chapter is concered with how to calibrate a computer model to observational data when the model produces multivariate output and is temporally expensive to run. The significance of considering models with long run times is that they can only be run at a limited number of different inputs, ruling out a brute-force Monte Carlo approach. Consequently, all inference must be done with a limited...

We consider parallel global optimization of derivative-free expensive-to-evaluate functions, and proposes an efficient method based on stochastic approximation for implementing a conceptual Bayesian optimization algorithm proposed by [10]. To accomplish this, we use infinitessimal perturbation analysis (IPA) to construct a stochastic gradient estimator and show that this estimator is unbiased.

What makes a good consistency ? Depending on the constraint, it may be a good pruning power or a low computational cost. By “weakening” arc-consistency, we propose to define new automatically generated solvers which form a sequence of consistencies weaker than arc-consistency. The method presented in this paper exploits a form of regularity in the cloud of constraint solutions: the density of s...

Running experiments on physical robotic systems typically requires significant resources (personnel, time, and money), restricting the number that can be run during training. Additionally, these systems typically operate over a range of external conditions and can be highly non-linear. We focus on the problem of learning a globally optimal policy to adapt controllers for such systems based on t...

Real world systems often have parameterized controllers which can be tuned to improve performance. Bayesian optimization methods provide for efficient optimization of these controllers, so as to reduce the number of required experiments on the expensive physical system. In this paper we address Bayesian optimization in the setting where performance is only observed through a stochastic binary o...

Many learning systems must confront the problem of run time after learning being greater than run time before learning. This utility problem has been a particular focus of research in explanation-based learning (EBL). This paper shows how the cost increase of a learned rule in an EBL system can be analyzed by characterizing the learning process as a sequence of transformations from a problem so...

Dear Editor: The world currently spends $100 billion annually on medical education [1]. This seems like a massive amount at a macroeconomic level. At a microeconomic level, medical school tuition fees in many countries are now as high as $14,000 per year. This will seem like a massive amount to an 18-year-old school leaver from an average financial background. Economic depressions make both fig...

One of the major goals of computer graphics is the rendering of realistic environments in real-time. One approach to this task is to use the newest features of graphics hardware to create complex effects which increase realism. The goal of this paper to propose a set of features which allows small environments to have comparable realism to much larger environments. These features will be geared...

There has been a surge of research interest in developing tools and analysis for Bayesian optimization, the task of finding the global maximizer of an unknown, expensive function through sequential evaluation using Bayesian decision theory. However, many interesting problems involve optimizing multiple, expensive to evaluate objectives simultaneously, and relatively little research has addresse...