A Statistical Perspective on Bayesian Deep Learning
Speaker: Nadja Klein (KIT - Karlsruhe Institute of Technology)
Bayesian deep learning fuses deep neural networks with Bayesian techniques to enable uncertainty quantification and enhance robustness in complex tasks such as image recognition or natural language processing. However, fully Bayesian estimation for neural networks is computationally intensive, requiring us to use approximate inference for virtually all practically relevant problems. Even for partially Bayesian neural networks, there is often a lack of clarity on how to adapt Bayesian principles to deep learning tasks, leaving practitioners overwhelmed by the theoretical aspects, such as choosing appropriate priors. So, how do we design scalable, reliable, and robust approximate Bayesian methods for deep learning? We address this question from a statistical perspective with a focus on ``combining the best of both worlds'' -- statistics and machine learning. We develop methods that deliver high-accuracy predictions and offer calibrated probabilistic confidence measures in those predictions. We showcase our work through real data examples and conclude with selected open challenges and directions for future research. The talk will start with a gentle introduction to Bayesian deep learning and tries to give intuitions rather than formulas.