Author Archive
Gaussian processes for modelling stellar activity and detecting planets
Speaker: Vinesh Rajpaul (Oxford) Abstract To date, the radial-velocity (RV) method has been one of the most productive techniques for detecting extrasolar planetary candidates. Unfortunately, stellar activity can induce RV variations which can drown out or even mimic planetary signals, and it is extremely difficult to model and thus mitigate these stellar effects. This is […]
Continue ReadingThe role of model selection, summary statistics and multiple-point statistics in Bayesian inverse problems: Examples from geophysics.
Lecturer: Niklas Linde (UNIL) Abstract Model selection and multiple-point statistics allow for comparisons of alternative conceptual descriptions of the system under study, while summary statistics (Approximate Bayesian Computation) allows us to relax some of the assumptions made in terms of observational, modelling and prior uncertainties. These concepts will be introduced and motivated with examples from […]
Continue ReadingConservative estimate for the excursion set of a deterministic function under a Gaussian random field model
Speaker: Dario Azzimonti (UniBern) Abstract The problem of estimating the excursion set of a deterministic function under a limited evaluation budget can be approached with Gaussian random field (GRF) modelling. Here we review two recent techniques based on Gaussian random field priors and we propose a fast algorithm to compute conservative estimates from the joint […]
Continue ReadingA journey through Gaussian random fields with a view towards Bayesian optimization.
Lecturer: David Ginsbourger (IDIAP / Uni Bern) Lecture abstract and outline. Gaussian random fields have been used as a flexible and practical family of priors in the context of Bayesian statistics when the parameter of interest is functional. In particular, these priors are now massively used in machine learning as a building block of adaptive […]
Continue ReadingPerforming Bayesian Model Selection with Nested Sampling
Lecturer: Farhan Feroz (Cambridge) Lecture abstract. Astrophysics and cosmology have increasingly become data driven with the availability of large amount of high quality data from missions like WMAP, Planck and LHC. This has resulted in Bayesian inference methods being widely used to analyse observations, but they can be extremely computationally demanding. I will discuss the […]
Continue ReadingBasic MCMC: implementing the Metropolis algorithm.
Lecturer: Daniel Mortlock (Imperial College London) Lecture abstract. Bayesian parameter inference consists of calculating Pr(theta | data, prior), the posterior distribution of the parameters, theta, conditional on whatever data is available (and some prior knowledge). In many situations it is hard to guess from the data what values of parameters are favoured, i.e., where the […]
Continue ReadingStatistical Inference
Lecturer: Adam Amara (ETHZ) Lecture topics. Probabilities: Joint, conditional and marginal -> on the road to Bayes Theorem. Dealing with full probability density functions in the case where a likelihood can be written -> grids, adaptive grids and MCMC. Linear models with Gaussian errors -> Generalised least square or regressions. Understanding the Chi^2 distribution and […]
Continue Reading
