
The Conference on Parsimony and Learning (CPAL) is an annual research conference focused on addressing the parsimonious, low dimensional structures that prevail in machine learning, signal processing, optimization, and beyond. We are interested in theories, algorithms, applications, hardware and systems, as well as scientific foundations for learning with parsimony.
Register for CPAL: March 23rd–26th, 2026
We are pleased to announce the Third Conference on Parsimony and Learning, to be hosted by the ELLIS Institute Tübingen, in conjunction with the Max Planck Institute for Intelligent Systems and the Tübingen AI Center.
All CPAL attendees are required to register. See the registration page for details about available tickets and costs.
CPAL 2026 Program Announced!
The CPAL 2026 review process is complete – congratulations to all authors of accepted papers!
The tentative program has been announced, and can be found on the schedule page. For information about the conference venue, see the logistics page.
Accepted papers for the Proceedings Track and Recent Spotlight Track have been released. Information about poster presentation sessions at CPAL can be found here. Information about oral sessions for Proceedings Track papers accepted as oral presentations can be found here.
Keynote Speakers
Information on the speakers’ planned talks is available here.

Francis Bach
INRIA - Ecole Normale Superieure

Matthias Bethge
University of Tubingen

Niao He
ETH Zurich

Andreas Krause
ETH Zurich

Yingyu Liang
University of Hong Kong, University of Wisconsin-Madison

Bernhard Scholkopf
Max Planck Institute for Intelligent Systems / ELLIS Institute Tubingen

Taiji Suzuki
University of Tokyo / RIKEN AIP

Jared Tanner
University of Oxford

Leena Chennuru Vankadara
University College London

Fanny Yang
ETH Zurich