Machine learning has been a fast growing field of research in several areas dealing with large datasets. We report recent progress on using RG ideas in the context of machine learning. We discuss the correspondence between principal components analysis (PCA) and RG flows across the transition for worm configurations of the 2D Ising model. More generally, we discuss the relationship between PCA and observables in MC data and the possibility of reduction of the number of learning parameters in supervised learning based on RG inspired hierarchical ansatzes.

Theoretical Developments