Deep Dive Workshop

Machine Learning Theory

Organized by:

Friday 9 October 10.05

Lead organizers: Nirupam Gupta, Tenure-Track Assistant Professor and Christian Igel, Full Professor, Department of Computer Science, University of Copenhagen

We welcome submissions of ongoing, recently published, or accepted work across all areas of ML theory, targeting MSc, PhD students, and postdocs.

Authors may submit for a long talk (20-30 minutes) or a poster with spotlight presentation, and may indicate willingness for either format. Tentative topics include (but not limited to) design and analysis of learning algorithms, optimization, online and reinforcement learning, deep learning theory, privacy, fairness and robustness.

Download Call for Participation

Submit an abstract (max 3000 characters) via this submission website

Programme

The session follows a workshop-style format combining invited talks, poster spotlight presentations, and an extended poster and networking session.

Welcome and introductory remarks (5 minutes)

Section 1 – Invited talks (50 minutes)

  • Long talk 1 (25 minutes): Invited speaker presentation (20 min) followed by Q&A (5 min)
  • Long talk 2 (25 minutes): Invited speaker presentation (20 min) followed by Q&A (5 min)

Section 2 – Poster spotlight session 1 (15 minutes)

7–8 short spotlight talks (2 minutes each) by poster presenters, giving a brief overview of their work to the full audience.

Break (10 minutes)

Section 3 – Invited talk (25 minutes)

Long talk 3 (25 minutes): Invited speaker presentation (20 min) followed by Q&A (5 min).

Section 4 – Poster spotlight session 2 (15 minutes)
7–8 short spotlight talks (2 minutes each) by poster presenters.

Section 5 – Poster session and open networking (60 minutes)
All poster presenters display their work. Participants circulate freely for in-depth discussion, feedback, and networking. This extended session is designed to foster new collaborations, particularly for PhD students and postdocs presenting their work.

Poster and spotlight contributions will be solicited through an open call. We welcome ongoing research, recently published work, open problems, and “theory for practice” presentations where applied AI challenges are posed for theoretical treatment.

Tentative speakers

Rasmus Pagh, Professor, University of Copenhagen:
Differential privacy and randomized algorithms for ML 

Aasa Feragen, Professor, Technical University of Denmark (DTU Compute):
Fairness, robustness, and geometric perspectives in ML

Andrea Paudice, Assistant Professor, Aarhus University:
Robust machine learning and optimization algorithms

Backups:
Amartya Sanyal, Assistant Professor, University of Copenhagen:
Privacy, robustness, and unlearning

Yevgeny Seldin, Professor, University of Copenhagen:
Online learning and PAC-Bayes generalization bounds

All tentative talk titles are indicative and will be finalized later.

Level

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

Organizers
  • Nirupam Gupta, (Lead organizer), Tenure-Track Assistant Professor, Department of Computer Science, University of Copenhagen, nigu@di.ku.dk
  • Christian Igel (Lead organizer), Full Professor, Department of Computer Science, University of Copenhagen, igel@di.ku.dk
  • Maria Astefanoaei, Assistant Professor, DASYA Lab, IT University of Copenhagen, msia@itu.dk
  • Kasper Green Larsen, Full Professor, Department of Computer Science, Aarhus University, larsen@cs.au.dk