@article{AcevedoDeWiljesReich2017, author = {Acevedo, Walter and De Wiljes, Jana and Reich, Sebastian}, title = {Second-order accurate ensemble transform particle filters}, series = {SIAM journal on scientific computing}, volume = {39}, journal = {SIAM journal on scientific computing}, number = {5}, publisher = {Society for Industrial and Applied Mathematics}, address = {Philadelphia}, issn = {1064-8275}, doi = {10.1137/16M1095184}, pages = {A1834 -- A1850}, year = {2017}, abstract = {Particle filters (also called sequential Monte Carlo methods) are widely used for state and parameter estimation problems in the context of nonlinear evolution equations. The recently proposed ensemble transform particle filter (ETPF) [S. Reich, SIAM T. Sci. Comput., 35, (2013), pp. A2013-A2014[ replaces the resampling step of a standard particle filter by a linear transformation which allows for a hybridization of particle filters with ensemble Kalman filters and renders the resulting hybrid filters applicable to spatially extended systems. However, the linear transformation step is computationally expensive and leads to an underestimation of the ensemble spread for small and moderate ensemble sizes. Here we address both of these shortcomings by developing second order accurate extensions of the ETPF. These extensions allow one in particular to replace the exact solution of a linear transport problem by its Sinkhorn approximation. It is also demonstrated that the nonlinear ensemble transform filter arises as a special case of our general framework. We illustrate the performance of the second-order accurate filters for the chaotic Lorenz-63 and Lorenz-96 models and a dynamic scene-viewing model. The numerical results for the Lorenz-63 and Lorenz-96 models demonstrate that significant accuracy improvements can be achieved in comparison to a standard ensemble Kalman filter and the ETPF for small to moderate ensemble sizes. The numerical results for the scene-viewing model reveal, on the other hand, that second-order corrections can lead to statistically inconsistent samples from the posterior parameter distribution.}, language = {en} } @article{BernerTrauthHolschneider2022, author = {Berner, Nadine and Trauth, Martin H. and Holschneider, Matthias}, title = {Bayesian inference about Plio-Pleistocene climate transitions in Africa}, series = {Quaternary science reviews : the international multidisciplinary research and review journal}, volume = {277}, journal = {Quaternary science reviews : the international multidisciplinary research and review journal}, publisher = {Elsevier}, address = {Oxford}, issn = {0277-3791}, doi = {10.1016/j.quascirev.2021.107287}, pages = {12}, year = {2022}, abstract = {During the last 5 Ma the Earth's ocean-atmosphere system passed through several major transitions, many of which are discussed as possible triggers for human evolution. A classic in this context is the possible influence of the closure of the Panama Strait, the intensification of Northern Hemisphere Glaciation, a stepwise increase in aridity in Africa, and the first appearance of the genus Homo about 2.5 - 2.7 Ma ago. Apart from the fact that the correlation between these events does not necessarily imply causality, many attempts to establish a relationship between climate and evolution fail due to the challenge of precisely localizing an a priori unknown number of changes potentially underlying complex climate records. The kernel-based Bayesian inference approach applied here allows inferring the location, generic shape, and temporal scale of multiple transitions in established records of Plio-Pleistocene African climate. By defining a transparent probabilistic analysis strategy, we are able to identify conjoint changes occurring across the investigated terrigenous dust records from Ocean Drilling Programme (ODP) sites in the Atlantic Ocean (ODP 659), Arabian (ODP 721/722) and Mediterranean Sea (ODP 967). The study indicates a two-step transition in the African climate proxy records at (2.35-2.10) Ma and (1.70 - 1.50) Ma, that may be associated with the reorganization of the Hadley-Walker Circulation. .}, language = {en} } @article{GarbunoInigoNueskenReich2020, author = {Garbuno-Inigo, Alfredo and N{\"u}sken, Nikolas and Reich, Sebastian}, title = {Affine invariant interacting Langevin dynamics for Bayesian inference}, series = {SIAM journal on applied dynamical systems}, volume = {19}, journal = {SIAM journal on applied dynamical systems}, number = {3}, publisher = {Society for Industrial and Applied Mathematics}, address = {Philadelphia}, issn = {1536-0040}, doi = {10.1137/19M1304891}, pages = {1633 -- 1658}, year = {2020}, abstract = {We propose a computational method (with acronym ALDI) for sampling from a given target distribution based on first-order (overdamped) Langevin dynamics which satisfies the property of affine invariance. The central idea of ALDI is to run an ensemble of particles with their empirical covariance serving as a preconditioner for their underlying Langevin dynamics. ALDI does not require taking the inverse or square root of the empirical covariance matrix, which enables application to high-dimensional sampling problems. The theoretical properties of ALDI are studied in terms of nondegeneracy and ergodicity. Furthermore, we study its connections to diffusion on Riemannian manifolds and Wasserstein gradient flows. Bayesian inference serves as a main application area for ALDI. In case of a forward problem with additive Gaussian measurement errors, ALDI allows for a gradient-free approximation in the spirit of the ensemble Kalman filter. A computational comparison between gradient-free and gradient-based ALDI is provided for a PDE constrained Bayesian inverse problem.}, language = {en} } @article{GianniotisSchnoerrMolkenthinetal.2016, author = {Gianniotis, Nikolaos and Schnoerr, Christoph and Molkenthin, Christian and Bora, Sanjay Singh}, title = {Approximate variational inference based on a finite sample of Gaussian latent variables}, series = {Pattern Analysis \& Applications}, volume = {19}, journal = {Pattern Analysis \& Applications}, publisher = {Springer}, address = {New York}, issn = {1433-7541}, doi = {10.1007/s10044-015-0496-9}, pages = {475 -- 485}, year = {2016}, abstract = {Variational methods are employed in situations where exact Bayesian inference becomes intractable due to the difficulty in performing certain integrals. Typically, variational methods postulate a tractable posterior and formulate a lower bound on the desired integral to be approximated, e.g. marginal likelihood. The lower bound is then optimised with respect to its free parameters, the so-called variational parameters. However, this is not always possible as for certain integrals it is very challenging (or tedious) to come up with a suitable lower bound. Here, we propose a simple scheme that overcomes some of the awkward cases where the usual variational treatment becomes difficult. The scheme relies on a rewriting of the lower bound on the model log-likelihood. We demonstrate the proposed scheme on a number of synthetic and real examples, as well as on a real geophysical model for which the standard variational approaches are inapplicable.}, language = {en} } @article{MalemShinitskiOjedaOpper2022, author = {Malem-Shinitski, Noa and Ojeda, Cesar and Opper, Manfred}, title = {Variational bayesian inference for nonlinear hawkes process with gaussian process self-effects}, series = {Entropy}, volume = {24}, journal = {Entropy}, number = {3}, publisher = {MDPI}, address = {Basel}, issn = {1099-4300}, doi = {10.3390/e24030356}, pages = {22}, year = {2022}, abstract = {Traditionally, Hawkes processes are used to model time-continuous point processes with history dependence. Here, we propose an extended model where the self-effects are of both excitatory and inhibitory types and follow a Gaussian Process. Whereas previous work either relies on a less flexible parameterization of the model, or requires a large amount of data, our formulation allows for both a flexible model and learning when data are scarce. We continue the line of work of Bayesian inference for Hawkes processes, and derive an inference algorithm by performing inference on an aggregated sum of Gaussian Processes. Approximate Bayesian inference is achieved via data augmentation, and we describe a mean-field variational inference approach to learn the model parameters. To demonstrate the flexibility of the model we apply our methodology on data from different domains and compare it to previously reported results.}, language = {en} } @article{MarionMcInernyPageletal.2012, author = {Marion, Glenn and McInerny, Greg J. and Pagel, J{\"o}rn and Catterall, Stephen and Cook, Alex R. and Hartig, Florian and O\&rsquo, and Hara, Robert B.}, title = {Parameter and uncertainty estimation for process-oriented population and distribution models: data, statistics and the niche}, series = {JOURNAL OF BIOGEOGRAPHY}, volume = {39}, journal = {JOURNAL OF BIOGEOGRAPHY}, number = {12}, publisher = {WILEY-BLACKWELL}, address = {HOBOKEN}, issn = {0305-0270}, doi = {10.1111/j.1365-2699.2012.02772.x}, pages = {2225 -- 2239}, year = {2012}, abstract = {The spatial distribution of a species is determined by dynamic processes such as reproduction, mortality and dispersal. Conventional static species distribution models (SDMs) do not incorporate these processes explicitly. This limits their applicability, particularly for non-equilibrium situations such as invasions or climate change. In this paper we show how dynamic SDMs can be formulated and fitted to data within a Bayesian framework. Our focus is on discrete state-space Markov process models which provide a flexible framework to account for stochasticity in key demographic processes, including dispersal, growth and competition. We show how to construct likelihood functions for such models (both discrete and continuous time versions) and how these can be combined with suitable observation models to conduct Bayesian parameter inference using computational techniques such as Markov chain Monte Carlo. We illustrate the current state-of-the-art with three contrasting examples using both simulated and empirical data. The use of simulated data allows the robustness of the methods to be tested with respect to deficiencies in both data and model. These examples show how mechanistic understanding of the processes that determine distribution and abundance can be combined with different sources of information at a range of spatial and temporal scales. Application of such techniques will enable more reliable inference and projections, e.g. under future climate change scenarios than is possible with purely correlative approaches. Conversely, confronting such process-oriented niche models with abundance and distribution data will test current understanding and may ultimately feedback to improve underlying ecological theory.}, language = {en} } @article{MillerSchwarz2011, author = {Miller, Jeff and Schwarz, Wolfgang}, title = {Aggregate and individual replication probability within an explicit model of the research process}, series = {Psychological methods}, volume = {16}, journal = {Psychological methods}, number = {3}, publisher = {American Psychological Association}, address = {Washington}, issn = {1082-989X}, doi = {10.1037/a0023347}, pages = {337 -- 360}, year = {2011}, abstract = {We study a model of the research process in which the true effect size, the replication jitter due to changes in experimental procedure, and the statistical error of effect size measurement are all normally distributed random variables. Within this model, we analyze the probability of successfully replicating an initial experimental result by obtaining either a statistically significant result in the same direction or any effect in that direction. We analyze both the probability of successfully replicating a particular experimental effect (i.e., the individual replication probability) and the average probability of successful replication across different studies within some research context (i.e., the aggregate replication probability), and we identify the conditions under which the latter can be approximated using the formulas of Killeen (2005a, 2007). We show how both of these probabilities depend on parameters of the research context that would rarely be known in practice. In addition, we show that the statistical uncertainty associated with the size of an initial observed effect would often prevent accurate estimation of the desired individual replication probability even if these research context parameters were known exactly. We conclude that accurate estimates of replication probability are generally unattainable.}, language = {en} } @article{MolkenthinDonnerReichetal.2022, author = {Molkenthin, Christian and Donner, Christian and Reich, Sebastian and Z{\"o}ller, Gert and Hainzl, Sebastian and Holschneider, Matthias and Opper, Manfred}, title = {GP-ETAS: semiparametric Bayesian inference for the spatio-temporal epidemic type aftershock sequence model}, series = {Statistics and Computing}, volume = {32}, journal = {Statistics and Computing}, number = {2}, publisher = {Springer}, address = {Dordrecht}, issn = {0960-3174}, doi = {10.1007/s11222-022-10085-3}, pages = {25}, year = {2022}, abstract = {The spatio-temporal epidemic type aftershock sequence (ETAS) model is widely used to describe the self-exciting nature of earthquake occurrences. While traditional inference methods provide only point estimates of the model parameters, we aim at a fully Bayesian treatment of model inference, allowing naturally to incorporate prior knowledge and uncertainty quantification of the resulting estimates. Therefore, we introduce a highly flexible, non-parametric representation for the spatially varying ETAS background intensity through a Gaussian process (GP) prior. Combined with classical triggering functions this results in a new model formulation, namely the GP-ETAS model. We enable tractable and efficient Gibbs sampling by deriving an augmented form of the GP-ETAS inference problem. This novel sampling approach allows us to assess the posterior model variables conditioned on observed earthquake catalogues, i.e., the spatial background intensity and the parameters of the triggering function. Empirical results on two synthetic data sets indicate that GP-ETAS outperforms standard models and thus demonstrate the predictive power for observed earthquake catalogues including uncertainty quantification for the estimated parameters. Finally, a case study for the l'Aquila region, Italy, with the devastating event on 6 April 2009, is presented.}, language = {en} } @article{RabeChandraKruegeletal.2021, author = {Rabe, Maximilian Michael and Chandra, Johan and Kr{\"u}gel, Andr{\´e} and Seelig, Stefan A. and Vasishth, Shravan and Engbert, Ralf}, title = {A bayesian approach to dynamical modeling of eye-movement control in reading of normal, mirrored, and scrambled texts}, series = {Psychological Review}, volume = {128}, journal = {Psychological Review}, number = {5}, publisher = {American Psychological Association}, address = {Washington}, issn = {0033-295X}, doi = {10.1037/rev0000268}, pages = {803 -- 823}, year = {2021}, abstract = {In eye-movement control during reading, advanced process-oriented models have been developed to reproduce behavioral data. So far, model complexity and large numbers of model parameters prevented rigorous statistical inference and modeling of interindividual differences. Here we propose a Bayesian approach to both problems for one representative computational model of sentence reading (SWIFT; Engbert et al., Psychological Review, 112, 2005, pp. 777-813). We used experimental data from 36 subjects who read the text in a normal and one of four manipulated text layouts (e.g., mirrored and scrambled letters). The SWIFT model was fitted to subjects and experimental conditions individually to investigate between- subject variability. Based on posterior distributions of model parameters, fixation probabilities and durations are reliably recovered from simulated data and reproduced for withheld empirical data, at both the experimental condition and subject levels. A subsequent statistical analysis of model parameters across reading conditions generates model-driven explanations for observable effects between conditions.}, language = {en} } @article{Reich2013, author = {Reich, Sebastian}, title = {A nonparametric ensemble transform method for bayesian inference}, series = {SIAM journal on scientific computing}, volume = {35}, journal = {SIAM journal on scientific computing}, number = {4}, publisher = {Society for Industrial and Applied Mathematics}, address = {Philadelphia}, issn = {1064-8275}, doi = {10.1137/130907367}, pages = {A2013 -- A2024}, year = {2013}, abstract = {Many applications, such as intermittent data assimilation, lead to a recursive application of Bayesian inference within a Monte Carlo context. Popular data assimilation algorithms include sequential Monte Carlo methods and ensemble Kalman filters (EnKFs). These methods differ in the way Bayesian inference is implemented. Sequential Monte Carlo methods rely on importance sampling combined with a resampling step, while EnKFs utilize a linear transformation of Monte Carlo samples based on the classic Kalman filter. While EnKFs have proven to be quite robust even for small ensemble sizes, they are not consistent since their derivation relies on a linear regression ansatz. In this paper, we propose another transform method, which does not rely on any a priori assumptions on the underlying prior and posterior distributions. The new method is based on solving an optimal transportation problem for discrete random variables.}, language = {en} }