The advent of the Big Data era has triggered a renewed interest in large-dimensional machine learning (ML) and (deep) neural networks. These methods, being developed from small-dimensional intuitions, often behave dramatically different from their original designs and tend to be inefficient on large-dimensional datasets. By assuming both dimension and size of the datasets to be large, recent advances in random matrix theory (RMT) provide novel insights, allowing for a renewed understanding and the possibility to design more efficient machine learning approaches, thereby opening the door to completely new paradigms.

In this talk, we will start with the “curse of dimensionality” phenomenon in high dimensions, and highlight many counterintuitive phenomena in ML that arise when large-dimensional data are considered. By focusing on the use case of neural network compression, and by considering the data dimension and/or the ML systems to be large, we discuss how RMT is able to provide a renewed understanding of modern ML.