2nd Workshop on High-dimensional Learning Dynamics (HiLD):

The Emergence of Structure and Reasoning

ICML 2024

Friday, July 26, 2024

Vienna, Austria

Description

Modeling learning dynamics has long been a goal of the empirical science and theory communities in deep learning. These communities have grown rapidly in recent years, as our newly expanded understanding of the latent structures and capabilities of large models permits researchers to study these phenomena through the lens of the training process. Recent progress in understanding fully trained models can therefore enable understanding of their development and lead to insights that improve optimizer and architecture design, provide model interpretations, inform evaluation, and generally enhance the science of neural networks and their priors.  The HiLD workshop seeks to spur research and collaboration around: 

This year the 2nd Workshop on High-dimensional Learning Dynamics theme is on The Emergence of Structure and Reasoning. We aim to foster discussion, discovery, and dissemination of state-of-the-art research in high-dimensional learning dynamics relevant to ML and bring together experts from all parts of ML: theorists to the empirical scientists.  It seeks to create synergies between these two groups which often do not interact. Through a series of talks, the workshop will tackle questions on high-dimensionality in ML. 

Topics

Include but not limited to:

Credit: Yuichiro Chino

Notification Timeline & Deadline

(*) If you face severe difficulties meeting this deadline, please contact us before the deadline. 

Submission of papers will be through OpenReview and limited to no more than 5 pages plus supplementary materials.


All submissions must be anonymized and may not contain any identifying information that may violate the double-blind reviewing policy.


For accepted workshop posters, please adhere to the following:

Stochastic Differential Equations (SDEs) & ML

Credit: Martin Barlow

Loss Landscapes of Neural Networks

Credit: https://losslandscape.com/gallery/

Random Matrix Theory (RMT) & ML


Credit: Yuichiro Chino

Dynamical Systems related to ML