Brendan Mallery

Tufts University

headshot.jpeg

Cambridge, MA 02139

brendanmallery9@gmail.com

CV · Google Scholar · GitHub

I am a 5th year PhD candidate in the mathematics department at Tufts University, working with Professors James Murphy and Shuchin Aeron.

My research focuses on:

  1. Representation learning for probability distributions with optimal transport;
  2. Geometric approaches to machine learning and data science;
  3. Interpretability and safety in AI, through the analysis of latent spaces in deep learning models.
  4. Modeling and analysis of time-evolving networks;

I have also published work in topological data analysis and geometric group theory.

Here are some pics from my research:

Synthesis and Analysis — Generating and reconstructing data as probability measures using entropy-regularized optimal transport.

Synthesis and Analysis

Dictionary Learning on LLM Document Embeddings — Visualizing unsupervised clustering of dictionary codes.

Latent Space

Robust Signal Recovery with Entropy-Regularized Barycenters — Point clouds with dropout noise can be recovered by projecting onto set of barycenters.

Reconstructions

Time-Evolving Curvature of Networks — Evolving cluster structure is detected using time-evolving Ricci curvature.