The DIMACS Workshop on Modeling Randomness in Neural Network Training: Mathematical, Statistical, and Numerical Guarantees was held at the DIMACS Center at Rutgers University from June 5-7, 2024. The central question of this workshop was: what can random matrix theory tell us about neural networks, modern machine learning, and AI?
One goal of the workshop was to create bridges between the different mathematical and computational communities by bringing together researchers with a diverse set of perspectives on neural networks. Topics of interest included:
- understanding matrix-valued random processes that arise during NN training,
- modeling/measuring uncertainty and designing estimators for training processes,
- applications to these designs within optimization algorithms.
DIMACS has set up a website for the workshop as well.