Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks

no code implementations • 6 Jun 2024 • Tristan Cinquin, Robert Bamler

Bayesian neural networks (BNN) promise to combine the predictive performance of neural networks with principled uncertainty modeling important for safety-critical systems and decision making.

Decision Making Out-of-Distribution Detection +1

Variational Boosted Soft Trees

no code implementations • 21 Feb 2023 • Tristan Cinquin, Tammo Rukat, Philipp Schmidt, Martin Wistuba, Artur Bekasov

Variational inference is often used to implement Bayesian neural networks, but is difficult to apply to GBMs, because the decision trees used as weak learners are non-differentiable.

Decision Making Out-of-Distribution Detection +3

Pathologies in priors and inference for Bayesian transformers

no code implementations • NeurIPS Workshop ICBINB 2021 • Tristan Cinquin, Alexander Immer, Max Horn, Vincent Fortuin

In recent years, the transformer has established itself as a workhorse in many applications ranging from natural language processing to reinforcement learning.

Bayesian Inference Variational Inference