Computational statistics

An information criterion for gradient boosted trees

Gradient boosting has been highly successful in machine-learning competitions for structured/tabular data since the introduction of XGBoost in 2014. Gradient boosting may be seen as a way of doing functional gradient descent to the supervised …

An information criterion for gradient boosted trees

Gradient boosting has been highly successful in machine-learning competitions for structured/tabular data since the introduction of XGBoost in 2014. Gradient boosting may be seen as a way of doing functional gradient descent to the supervised …

Information criteria for gradient boosted trees: Adaptive tree size and early stopping

In gradient tree boosting, the functional form of the ensemble repeatedly changes during training. To select a sensible functional complexity for the boosting ensemble, the leading implementations offer a high number of hyperparameters for …

spaTMB

Using TMB to build the saddlepoint approximation.

Saddlepoint adjusted inversion of characteristic functions

For certain types of statistical models, the characteristic function (Fourier transform) is available in closed form, whereas the probability density function has an intractable form, typically as an infinite sum of probability weighted densities. …

SPI

Saddlepoint adjusted inversion of characteristic functions.

Saddlepoint adjusted inversion of characteristic functions

For certain types of statistical models, the characteristic function (Fourier transform) is available in closed form, whereas the probability density function has an intractable form, typically as an infinite sum of probability weighted densities. …

Finance in the frequency domain

The Fourier transform from the time-domain to the frequency-domain is a powerful tool for an abundance of applications. In this lecture, the focus is on that of finance and risk. A brief introduction to the Fourier transform is given, and then an …

Likelihood Estimation of Jump-Diffusions: Extensions from Diffusions to Jump-Diffusions, Implementation with Automatic Differentiation, and Applications

This lecture considers the problem of likelihood-based parameter estimation for time-homoge- neous jump-diffusion processes. The problem is that there often is no analytic solution to the stochastic differential equations driving the process. Thus, …

Likelihood Estimation of Jump-Diffusions: Extensions from Diffusions to Jump-Diffusions, Implementation with Automatic Differentiation, and Applications

This thesis considers the problem of likelihood- based parameter estimation for time-homogeneous jump-diffusion processes. The problem is that there often is no analytic solution to the stochastic differential equations driving the process. Thus, the …