Deep generative models such as deep latent Gaussian models (DLGMs) are powerful and popular density estimators. However, they have been applied almost exclusively to dense data such as images; DLGMs are rarely applied to sparse, high-dimensional integer data such as word counts or product ratings. One reason is that the standard training procedures find poor local optima when applied to such da...

The majority of the literature on the psychology of gains and losses suggests that losses lead to an avoidance response. Several studies, however, have shown that losses can also lead to an approach response, whereby an option is selected more often when it produces losses. In five studies we examine the boundary conditions for these contradictory approach and avoidance effects. The results sho...

This paper presents a simple and locally optimal test for Zipf’s law. Its use is illustrated in the case of the largest US metropolitan areas. An objection to the general relevance of that law is also presented.  2000 Elsevier Science S.A. All rights reserved.

Escaping local optima and crossing fitness valleys to reach higher-fitness regions of a fitness landscape is a ubiquitous concept in much writing on evolutionary difficulty. The Baldwin effect, an interaction between non-heritable lifetime plasticity (e.g. learning) and evolution, has been shown to be able to guide evolutionary change and ‘smooth out’ abrupt fitness changes in fitness landscape...