Normalizing flows for probabilistic modeling and inference

G Papamakarios, E Nalisnick, DJ Rezende… - Journal of Machine …, 2021 - jmlr.org
Normalizing flows provide a general mechanism for defining expressive probability
distributions, only requiring the specification of a (usually simple) base distribution and a …

Robot learning from randomized simulations: A review

F Muratore, F Ramos, G Turk, W Yu… - Frontiers in Robotics …, 2022 - frontiersin.org
The rise of deep learning has caused a paradigm shift in robotics research, favoring
methods that require large amounts of data. Unfortunately, it is prohibitively expensive to …

Real-time gravitational wave science with neural posterior estimation

M Dax, SR Green, J Gair, JH Macke, A Buonanno… - Physical review …, 2021 - APS
We demonstrate unprecedented accuracy for rapid gravitational wave parameter estimation
with deep learning. Using neural networks as surrogates for Bayesian posterior distributions …

SBI--A toolkit for simulation-based inference

A Tejero-Cantero, J Boelts, M Deistler… - arXiv preprint arXiv …, 2020 - arxiv.org
Scientists and engineers employ stochastic numerical simulators to model empirically
observed phenomena. In contrast to purely statistical models, simulators express scientific …

Benchmarking simulation-based inference

JM Lueckmann, J Boelts, D Greenberg… - International …, 2021 - proceedings.mlr.press
Recent advances in probabilistic modelling have led to a large number of simulation-based
inference algorithms which do not require numerical evaluation of likelihoods. However, a …

Simulation intelligence: Towards a new generation of scientific methods

A Lavin, D Krakauer, H Zenil, J Gottschlich… - arXiv preprint arXiv …, 2021 - arxiv.org
The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Training deep neural density estimators to identify mechanistic models of neural dynamics

PJ Gonçalves, JM Lueckmann, M Deistler… - Elife, 2020 - elifesciences.org
Mechanistic modeling in neuroscience aims to explain observed phenomena in terms of
underlying causes. However, determining which model parameters agree with complex and …

BayesFlow: Learning complex stochastic models with invertible neural networks

ST Radev, UK Mertens, A Voss… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Estimating the parameters of mathematical models is a common problem in almost all
branches of science. However, this problem can prove notably difficult when processes and …

Truncated proposals for scalable and hassle-free simulation-based inference

M Deistler, PJ Goncalves… - Advances in Neural …, 2022 - proceedings.neurips.cc
Simulation-based inference (SBI) solves statistical inverse problems by repeatedly running a
stochastic simulator and inferring posterior distributions from model-simulations. To improve …

Likelihood-free mcmc with amortized approximate ratio estimators

J Hermans, V Begy, G Louppe - International conference on …, 2020 - proceedings.mlr.press
Posterior inference with an intractable likelihood is becoming an increasingly common task
in scientific domains which rely on sophisticated computer simulations. Typically, these …