The FOXBOX system puts in practice the black box representation of symbolic objects and provides algorithms for performing the symbolic calculus with such representations. Black box objects are stored as functions. For instance: a black box polynomial is a procedure that takes values for the variables as input and evaluates the polynomial at that given point. FOXBOX can compute the greatest com...

In many areas of science and engineering researchers consider systems that can be solely examined by their input and output characteristics without any knowledge of their internal workings. Such black-box systems are the topic of the present thesis. In many practical cases, a black box comprises a complex mathematical model, a computer simulation, a real-world experiment, or a combination of an...

We present a semiclassical method for determining the effective low-energy quantum Hamiltonian of weakly anharmonic superconducting circuits containing mesoscopic Josephson junctions coupled to electromagnetic environments made of an arbitrary combination of distributed and lumped elements. A convenient basis, capturing the multimode physics, is given by the quantized eigenmodes of the lineariz...

We introduce overdispersed black-box variational inference, a method to reduce the variance of the Monte Carlo estimator of the gradient in black-box variational inference. Instead of taking samples from the variational distribution, we use importance sampling to take samples from an overdispersed distribution in the same exponential family as the variational approximation. Our approach is gene...

Black box variational inference (BBVI) with reparameterization gradients triggered the exploration of divergence measures other than the Kullback-Leibler (KL) divergence, such as alpha divergences. In this paper, we view BBVI with generalized divergences as a form of estimating the marginal likelihood via biased importance sampling. The choice of divergence determines a bias-variance trade-off ...

We show that the black-box complexity with memory restriction one of the n-dimensional OneMax function class is at most 2n. This disproves the Θ(n log n) conjecture of Droste, Jansen, and Wegener (Theory of Computing Systems 39 (2006) 525–544).

With increasing complexity of machine learning systems being used1, there is a crucial need for providing insights into what these models are doing. Model-agnostic approaches [18], such as Baehrens et al. [1] and Ribeiro et al. [17], have shown that insights into complex, black-box models do not have to come at a cost of accuracy, and that accurate local explanations can successfully be provide...

Many interactive environments can be represented as games, but they are so large and complex that individual players are mostly in the dark about others’ actions and the payoff structure. This paper analyzes learning behavior in such ‘black box’ environments, where players’ only source of information is their own history of actions taken and payoffs received. The context of our analysis are dec...

Opening a model of the learner is a potentially complex operation. There are many aspects of the learner that can be modelled, and many of these aspects may need to be opened in different ways. In addition, there may be complicated interactions between these aspects which raise questions both about the accuracy of the underlying model and the methods for representing a holistic view of the mode...