Machine learning (ML) theory provides the foundational understanding of AI methodology. Despite the active involvement of the Danish research community in contributing to major ML venues, there should be more regular meetings focused on ML theory within Denmark.

Building on the success of the first D3A conference, we continue to make D3A a recurring meeting point for those interested in ML theory. This session will offer a space to present new results, share ideas, and discuss potential collaborations, both within theoretical ML research and between theory and practical applications.

Main activities / tentative schedule

0-5 minutes: Welcome

5-75 minutes: Three talks by invited speakers

75-90 minutes:  Panel discussion:
How do we strengthen the machine learning theory community? What are the major open theoretical questions in machine learning and how will their solution impact machine learning and artificial intelligence?

List of speakers

• Amir Yehudayoff, KU, amir.yehudayoff@gmail.com
• Chris Schwiegelshohn, AU, schwiegelshohn@cs.au.dk
• Nicklas Werge, SDU, werge@sdu.dk

Organizers

• Yi-Shan Wu, lead organizer, SDU, yswu@imada.sdu.dk
• Christian Igel, KU, igel@di.ku.dk
• Ole Winther, KU and DTU, olwi@dtu.dk

Level

Intermediate. For attendees who have basic understanding or some experience with the subject but are not yet advanced.