As a member of both Stefano Profumo’s SCIPP Theory group at UC Santa Cruz and Joseph Hennawi’s ENIGMA group at UC Santa Barbara and Leiden Observatory, I work at the intersection of physics, deep learning, and statistics.
In my time as a graduate student, I’ve been lucky enough to work on projects with the world’s leading experts on applied deep learning. I have worked on deepening (pun intended) the understanding of current theories for a variety of topics: From beyond standard model particle (high energy/astro)physics, to the structure of the Milky Way, and the cosmological history of the universe.
Recent publications
Simulation Based Inference for Efficient Theory Space Sampling: an Application to Supersymmetric Explanations of the Anomalous Muon (g-2)
Application of bleeding-edge approximate inference algorithms to improve understanding of highly-parameterized theoretical models.
Via Machinae: Searching for Stellar Streams using Unsupervised Machine Learning
Unsupervised deep anomaly detection to discover unknown substructure in the Milky Way.
Fully probabilistic quasar continua predictions near Lyman-α with conditional neural spline flows
SOTA algorithm that fully characterizes the high-dimensional Bayesian inference problem.
Extreme Deconvolution of Conditional Mixture Density Networks
Novel density estimation algorithm at the intersection of classical and modern machine learning.
Projects ands Posts
SaxBI
All-in-one implementation of simulation-based inference algorithms written in JAX.
Update your Jax seeds!
Illustrating the importance of maintaining good RNG practices and demonstrating subtle issues that can arise.