Embrace the challenges of intractable likelihoods with Simulation-based inference! A half-day workshop introducing the concepts theoretically and practically.

In traditional statistical inference, the likelihood function — a function of the parameters given the data — is central to both Bayesian and frequentist methods. However, when the likelihood is intractable, standard techniques such as maximum likelihood estimation or Markov Chain Monte Carlo cannot be applied directly.

Simulation-based inference (SBI) is a key approach within likelihood-free inference methods to circumvent this problem.

What to expect

This training provides the participants with a thorough understanding of the fundamental principles and methods of Simulation-based Inference, including why and when to use these methods in place of traditional likelihood-based inference techniques. Participants can also expect to learn how to apply and evaluate the performance of Simulation-based Inference techniques in real-world scenarios, including how to model, simulate, and make inferences from data in a practical context.

• Grasp SBI principles & applications
• Learn neural network-based density estimation
• Implement SBI methods in real-world cases
• Evaluate approximations with quality metrics

Contents

• Introduction to Simulation-based Inference
• Neural Density Estimation
• Sequential Neural Posterior Estimation
• Performance Assessment

Check out the full description of the training on our website.

Disclaimer:

The appliedAI Institute for Europe gGmbH is supported by the KI-Stiftung Heilbronn gGmbH. The appliedAI Institute for Europe gGmbH is a subsidiary of the appliedAI Initiative GmbH.

Read about this training on the TransferLab website