Matt Raymond

PhD candidate, co-advised by Dr. Violi and Dr. Scott

mattrmd2024.jpg

My research is at the intersection of Machine Learning (ML) theory and Computational (Bio)Chemistry applications. Currently, I’m interested in developing generalized frameworks for ML in chemistry, which has applications in drug discovery, the prediction of macromolecular interactions, and exploration of biochemical reactions. Previous interests include multitask feature selection, surrogate modeling of plasma physics, detection of cross-feeding interactions in the human gut microbiome, the implicit bias of multiclass logistic regression, artificially-curious agents for space exploration, and the handling of catastrophic errors for real-time flight software.

I received my BSc in Computer Science (‘20, Magna Cum Laude) from Chapman University and my MSc in Computer Science and Engineering from the University of Michigan (‘22). I am current studying for my PhD in Electrical and Computer Engineering at the University of Michigan, specializing in Signal and Image Processing and Machine Learning. Ideally, I will be graduating sometime around Spring 2026.

News

Aug 23, 2024 My poster Joint Optimization Significantly Improves Gradient Boosting received a “top 15” award at the 2024 Midwest Machine Learning Symposium (MMLS), which includes a $500 prize. This poster contained preliminary results for Joint Optimization of Piecewise Linear Ensembles.
Jul 12, 2024 Joint Optimization of Piecewise Linear Ensembles has been accepted to the 2024 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)! Code release available on this PyPI repository using pip install joplen.
Jun 28, 2024 The U of M ECE department has provided a press release on my 2024-2025 J. Robert Beyster Computational Innovation Graduate Fellowship with details on my past and present research.
Jun 12, 2024 I have just received the 2024-2025 J. Robert Beyster Computational Innovation Graduate Fellowship for my work in machine learning in computational chemistry, with applications in nanomedicine. This fellowship covers one year of tuition, stipend, and health insurance. Many thanks to my advisors Angela Violi and Clayton Scott, and to Paolo Elvati for their support and guidance!
May 22, 2024 I gave a talk and a poster presentation on Geometric Deep Learning and its use for accelating molecular dynamics simulations of nonthermal plasma at the 2024 Dusty Plasma Workshop in Minneapolis, MN. The abstract can be seen here.