On trend estimation under monotone Gaussian subordination with long-memory: application to fossil pollen series

Fossil pollen data from stratigraphic cores are irregularly spaced in time due to non-linear age-depth relations. Moreover, their marginal distributions may vary over time. We address these features in a nonparametric regression model with errors that are monotone transformations of a latent continuous-time Gaussian process Z(T). Although Z(T) is unobserved, due to monotonicity, under suitable regularity conditions, it can be recovered facilitating further computations such as estimation of the long-memory parameter and the Hermite coefficients. The estimation of Z(T) itself involves estimation of the marginal distribution function of the regression errors. These issues are considered in proposing a plug-in algorithm for optimal bandwidth selection and construction of confidence bands for the trend function. Some high-resolution time series of pollen records from Lago di Origlio in Switzerland, which go back ca. 20,000 years are used to illustrate the methods.

Estimating and quantifying uncertainties on level sets using the Vorob'ev expectation and deviation with Gaussian process models

Several methods based on Kriging have recently been proposed for calculating a probability of failure involving costly-to-evaluate functions. A closely related problem is to estimate the set of inputs leading to a response exceeding a given threshold. Now, estimating such a level set—and not solely its volume—and quantifying uncertainties on it are not straightforward. Here we use notions from random set theory to obtain an estimate of the level set, together with a quantification of estimation uncertainty. We give explicit formulae in the Gaussian process set-up and provide a consistency result. We then illustrate how space-filling versus adaptive design strategies may sequentially reduce level set estimation uncertainty.

A Nonstationary Space-Time Gaussian Process Model for Partially Converged Simulations

In the context of expensive numerical experiments, a promising solution for alleviating the computational costs consists of using partially converged simulations instead of exact solutions. The gain in computational time is at the price of precision in the response. This work addresses the issue of fitting a Gaussian process model to partially converged simulation data for further use in prediction. The main challenge consists of the adequate approximation of the error due to partial convergence, which is correlated in both design variables and time directions. Here, we propose fitting a Gaussian process in the joint space of design parameters and computational time. The model is constructed by building a nonstationary covariance kernel that reflects accurately the actual structure of the error. Practical solutions are proposed for solving parameter estimation issues associated with the proposed model. The method is applied to a computational fluid dynamics test case and shows significant improvement in prediction compared to a classical kriging model.

Tuning curve of type-0 spontaneous parametric down-conversion

We study the tuning curve of entangled photons generated by type-0 spontaneous parametric down-conversion in a periodically poled potassium titanyl phosphate crystal. We demonstrate the X-shaped spatiotemporal structure of the spectrum by means of measurements and numerical simulations. Experiments for different pump waists, crystal temperatures, and crystal lengths are in good agreement with numerical simulations.

Palynological richness and evenness: insights from the taxa accumulation curve

Palynology provides the opportunity to make inferences on changes in diversity of terrestrial vegetation over long time scales. The often coarse taxonomic level achievable in pollen analysis, differences in pollen production and dispersal, and the lack of pollen source boundaries hamper the application of diversity indices to palynology. Palynological richness, the number of pollen types at a constant pollen count, is the most robust and widely used diversity indicator for pollen data. However, this index is also influenced by the abundance distribution of pollen types in sediments. In particular, where the index is calculated by rarefaction analysis, information on taxonomic richness at low abundance may be lost. Here we explore information that can be extracted from the accumulation of taxa over consecutive samples. The log-transformed taxa accumulation curve can be broken up into linear sections with different slope and intersect parameters, describing the accumulation of new taxa within the section. The breaking points may indicate changes in the species pool or in the abundance of high versus low pollen producers. Testing this concept on three pollen diagrams from different landscapes, we find that the break points in the taxa accumulation curves provide convenient zones for identifying changes in richness and evenness. The linear regressions over consecutive samples can be used to inter- and extrapolate to low or extremely high pollen counts, indicating evenness and richness in taxonomic composition within these zones. An evenness indicator, based on the rank-order-abundance is used to assist in the evaluation of the results and the interpretation of the fossil records. Two central European pollen diagrams show major changes in the taxa accumulation curves for the Lateglacial period and the time of human induced land-use changes, while they do not indicate strong changes in the species pool with the onset of the Holocene. In contrast, a central Swedish pollen diagram shows comparatively little change, but high richness during the early Holocene forest establishment. Evenness and palynological richness are related for most periods in the three diagrams, however, sections before forest establishment and after forest clearance show high evenness, which is not necessarily accompanied by high palynological richness, encouraging efforts to separate the two.

Uniqueness of the Embedding Continuous Convolution Semigroup of a Gaussian Probability Measure on the Affine Group and an Application in Mathematical Finance

Let {μ(i)t}t≥0 ( i=1,2 ) be continuous convolution semigroups (c.c.s.) of probability measures on Aff(1) (the affine group on the real line). Suppose that μ(1)1=μ(2)1 . Assume furthermore that {μ(1)t}t≥0 is a Gaussian c.c.s. (in the sense that its generating distribution is a sum of a primitive distribution and a second-order differential operator). Then μ(1)t=μ(2)t for all t≥0 . We end up with a possible application in mathematical finance.

Quantifying uncertainty on Pareto fronts with Gaussian process conditional simulations

Multi-objective optimization algorithms aim at finding Pareto-optimal solutions. Recovering Pareto fronts or Pareto sets from a limited number of function evaluations are challenging problems. A popular approach in the case of expensive-to-evaluate functions is to appeal to metamodels. Kriging has been shown efficient as a base for sequential multi-objective optimization, notably through infill sampling criteria balancing exploitation and exploration such as the Expected Hypervolume Improvement. Here we consider Kriging metamodels not only for selecting new points, but as a tool for estimating the whole Pareto front and quantifying how much uncertainty remains on it at any stage of Kriging-based multi-objective optimization algorithms. Our approach relies on the Gaussian process interpretation of Kriging, and bases upon conditional simulations. Using concepts from random set theory, we propose to adapt the Vorob’ev expectation and deviation to capture the variability of the set of non-dominated points. Numerical experiments illustrate the potential of the proposed workflow, and it is shown on examples how Gaussian process simulations and the estimated Vorob’ev deviation can be used to monitor the ability of Kriging-based multi-objective optimization algorithms to accurately learn the Pareto front.

Bounding Standard Gaussian Tail Probabilities

We review various inequalities for Mills' ratio (1 - Φ)= Ø, where Ø and Φ denote the standard Gaussian density and distribution function, respectively. Elementary considerations involving finite continued fractions lead to a general approximation scheme which implies and refines several known bounds.