The paper proposes Metropolis adjusted Langevin and Hamiltonian Monte Carlo sampling
methods defined on the Riemann manifold to resolve the shortcomings of existing Monte …

Even simple examples of finite mixture models can fail to fulfil the regularity conditions that
are routinely assumed in standard parametric inference problems. Many methods have …

Abstract Sampling and Variational Inference (VI) are two large families of methods for
approximate inference that have complementary strengths. Sampling methods excel at …

One of the main topics in signal processing is the reconstruction of a signal from a set of
measurements. Similarly, in statistics, much interest pertains to finding a ground truth …

A new class of local mixture models called local scale mixture models is introduced. This
class is particularly suitable for the analysis of mixtures of the exponential distribution. The …

In this paper we study ideals arising from moments of local Dirac measures and their
mixtures. We provide generators for the case of first order local Diracs and explain how to …

Mixture models provide a natural framework for unobserved heterogeneity in a population.
They are widely applied in astronomy, biology, engineering, finance, genetics, medicine …

We give a personal view of what Information Geometry is, and what it is becoming, by
exploring a number of key topics: dual affine families, boundaries, divergences, tensorial …

Despite the flexibility and popularity of mixture models, their associated parameter spaces
are often difficult to represent due to fundamental identification problems. This paper looks at …

One of the main themes in the field of algebraic statistics is the application of algebraic tools
to statistics. More concretely, methods from combinatorial and computational algebra and …