Lasse Elsemüller
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lasse Elsemüller has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Paul-Christian Bürkner
Department of Statistics, TU Dortmund University, Dortmund, Germany
2 shared publications - Stefan T. Radev
Cognitive Science Department, Rensselaer Polytechnic Institute
2 shared publications - Lukas Schumacher
University of Basel, Basel, Switzerland
1 shared publication - Martin Schnuerch
Department of Psychology, School of Social Sciences, University of Mannheim
1 shared publication Marvin Schmitt
1 shared publication- Ullrich Köthe
Heidelberg University
1 shared publication
Latest Publications
- 6 May 2024
- Published by American Psychological Association (APA) in Psychological Methods
- Vol. 31 (5) , 917-945
A deep learning method for comparing Bayesian hierarchical models.
Bayesian model comparison (BMC) offers a principled approach to assessing the relative merits of competing computational models and propagating uncertainty into model selection decisions. However, BMC is often intractable for the popular class of hierarchical models due to their high-dimensional nested parameter structure. To address this intractability, we propose a deep learning method for performing BMC on any set of hierarchical models which can be instantiated as probabilistic programs. Since our method enables amortized inference, it allows efficient re-estimation of posterior model probabilities and fast performance validation prior to any real-data application. In a series of extensive validation studies, we benchmark the performance of our method against the state-of-the-art bridge sampling method and demonstrate excellent amortized inference across all BMC settings. We then showcase our method by comparing four hierarchical evidence accumulation models that have previously been deemed intractable for BMC due to partly implicit likelihoods. Additionally, we demonstrate how transfer learning can be leveraged to enhance training efficiency. We provide reproducible code for all analyses and an open-source implementation of our method. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
- 6 May 2024
- Published by American Psychological Association (APA) in Psychological Methods
- Vol. 31 (5) , 917-945
A deep learning method for comparing Bayesian hierarchical models.
Bayesian model comparison (BMC) offers a principled approach to assessing the relative merits of competing computational models and propagating uncertainty into model selection decisions. However, BMC is often intractable for the popular class of hierarchical models due to their high-dimensional nested parameter structure. To address this intractability, we propose a deep learning method for performing BMC on any set of hierarchical models which can be instantiated as probabilistic programs. Since our method enables amortized inference, it allows efficient re-estimation of posterior model probabilities and fast performance validation prior to any real-data application. In a series of extensive validation studies, we benchmark the performance of our method against the state-of-the-art bridge sampling method and demonstrate excellent amortized inference across all BMC settings. We then showcase our method by comparing four hierarchical evidence accumulation models that have previously been deemed intractable for BMC due to partly implicit likelihoods. Additionally, we demonstrate how transfer learning can be leveraged to enhance training efficiency. We provide reproducible code for all analyses and an open-source implementation of our method. (PsycInfo Database Record (c) 2024 APA, all rights reserved).
- Open Access
- 22 September 2023
- Published by The Open Journal in Journal of Open Source Software
- Vol. 8 (89) , 5702
BayesFlow: Amortized Bayesian Workflows With Neural Networks
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis (Bürkner et al., 2022; Gelman et al., 2020; Schad et al., 2021). Typical problems in Bayesian workflows are the approximation of intractable posterior distributions for diverse model types and the comparison of competing models of the same process in terms of their complexity and predictive performance. However, despite their theoretical appeal and utility, the practical execution of Bayesian workflows is often limited by computational bottlenecks: Obtaining even a single posterior may already take a long time, such that repeated estimation for the purpose of model validation or calibration becomes completely infeasible.
- 22 September 2023
- Published by The Open Journal in Journal of Open Source Software
- Vol. 8 (89) , 5702
Open AccessBayesFlow: Amortized Bayesian Workflows With Neural Networks
Modern Bayesian inference involves a mixture of computational techniques for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows for data analysis (Bürkner et al., 2022; Gelman et al., 2020; Schad et al., 2021). Typical problems in Bayesian workflows are the approximation of intractable posterior distributions for diverse model types and the comparison of competing models of the same process in terms of their complexity and predictive performance. However, despite their theoretical appeal and utility, the practical execution of Bayesian workflows is often limited by computational bottlenecks: Obtaining even a single posterior may already take a long time, such that repeated estimation for the purpose of model validation or calibration becomes completely infeasible.