In this thesis proposal, we propose and analyze new theories of clustering, one of the most fundamental tasks in machine learning. We use methods drawing from multiple disciplines, including metric embeddings, spectral algorithms, and group representation theory.
Each of these contributions answers natural questions in machine learning theory. For each of these contributions, we develop multidisciplinary tools. For ongoing and future work, we propose to apply these tools to a wider range of natural machine learning problems.
Gary Miller (Chair)
Satish Rao (University of California, Berkeley)
Zoom Participation. See announcement.