JavaScript is Disabled
Your browser's JavaScript functionality is disabled. It has to be enabled to use this function of ConfTool.
Here you can find information on how to enable JavaScript
If you have any problems, please contact the organizers at HAICON26@fu-confirm.de.

Conference Agenda

Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).

Only Sessions at Date / Time

Agenda Overview

Session

TT 9a - Deep Learning with Bayesian Principles

Time:

Monday, 08/June/2026:

9:00am - 11:00am

Location: Track 9

Session Abstract

Brief Description and Outline:

The tutorial covers both practical tools to obtain uncertainty estimates in deep learning, as well as a theoretical understanding of various deep learning phenomena through a Bayesian lens.

Outline:

Part 1 -- Foundations of Bayesian Principles for Deep Learning (30 minutes)

Part 2 -- Practical Tools (60 Minutes)

2.1: Variational Methods (45 Minutes)

2.2: Laplace Approximations (15 Minutes)

Part 3: Understanding Deep Learning via Bayesian Principles (30 Minutes)

References [1] https://arxiv.org/abs/2107.04562 [2.1] https://arxiv.org/abs/2402.17641 https://github.com/team-approx-bayes/ivon [2.2] https://arxiv.org/abs/2106.14806 https://github.com/aleximmer/Laplace [3] https://arxiv.org/abs/2110.11216 https://arxiv.org/abs/2503.02113

Goals:

After completion of the tutorial, participants will understand:

Learn how to use recent practical tools (Variational Learning and Laplace Approximations) to obtain uncertainty estimates for deep neural networks

Understand how these uncertainty estimates can be used in practice

A better understanding of generalization in deep learning and phenomena such as overfitting, double descent, grokking, which helps to answer questions such as: "How big should my model be"?

Deep learning has become the go-to choice for many practical problems (including ones that HAICON26 attendants might be interested in).

The tutorial teaches

1) practical tools that enables practitioners to obtain uncertainty estimates

2) an understanding how these uncertainty estimates can be used to improve models

3) obtain a better understanding of various mysterious phenomena in deep learning.

Presenters Experience:

Thomas Moellenhoff is a Senior Research Scientist at the RIKEN Center for Advanced Intelligence Project in Tokyo, Japan. He received his PhD in 2020 from the Technical University of Munich, under the supervision of Daniel Cremers. After that, he was a post-Doc from 2020-2023 working with Emtiyaz Khan at RIKEN AIP. His research lies in the intersection of optimization and Bayesian deep learning. He has co-organized several workshops, including the ICML 2023 workshop on duality principles in modern machine learning. His homepage is: https://moellenh.github.io

Target Audience:

The target audience are students (both undergraduate and master/PhD level) as well as researchers and practitioners from applied fields and industry. Prerequisites are basic mathematics (linear algebra, probability, calculus) and some previous experience with machine learning and deep learning.

Keywords:

deep learning, uncertainty quantification, bayesian deep learning, variational inference