Learning dynamics of machine learning (ML) algorithms, especially under the assumptions of high-dimensional datasets,  is enjoying tremendous growth as a field in ML.  It provides theoretical guarantees and tools to explain lots of ML phenomena seen in practical applications. Tools from stochastic differential equations (SDEs), high-dimensional probability, and random matrix theory  (RMT) are regularly employed as techniques to model high-dimensional data and trajectories of optimization algorithms. The HLD workshop seeks to spur research and collaboration around:

1. Developing analyzable models and dynamics to explain observed deep neural network phenomena;

2. Creating mathematical frameworks for scaling limits of neural network dynamics as width and depth grow;

3. Provably explaining the role of the optimization algorithm, hyper-parameter choices, and neural network architectural choices on training/test dynamics;

4. High-dimensionality, where intuitions from low-dimensional geometry tend to lead to inaccurate (and often misleading) properties of the machine learning models on large real-world datasets. 

The Workshop on High-dimensional Learning Dynamics aims to bring together experts from classical RMT, high-dimensional statistics/probability, and SDEs to share their perspectives on dynamics of ML algorithms while leveraging crossover experts in ML. 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 dynamics of algorithms at the interface of RMT, high-dimensional statistics, SDEs, and ML.