Applied Mathematics/Data Science Journal Club

Welcome to the Applied Math/Data Science Journal Club! The club is open to anyone interested in learning what applied math has to say about data science or recent machine learning methods that have already made a great impact on scientific computing. Selected topics so far include applied analysis of neural networks, data-driven equation discovery, generative modeling, and numerics for high-dimensional PDE. If you have any questions about the club, please contact us.

Spring semester meetings will take place on Tuesdays at 3:00 P.M. in Moody Hall Room 241

Club Schedule: Fall 2023

Topic/Article Discussion Leader Date Supplementary Materials
Organizational Meeting N/A October 23, 2023 N/A
The Modern Mathematics of Deep Learning, Berner, et al. Jimmie Adriazola November 20, 2023 Notes
The Modern Mathematics of Deep Learning, Berner, et al. Jimmie Adriazola December 4, 2023 Notes

Club Schedule: Spring 2024

Topic/Article Discussion Leader Date
The Bayesian Approach To Inverse Problems Austin Marstaller January 16, 2024
Denoising Diffusion Probabilistic Models Jimmie Adriazola January 23, 2024
Discovering governing equations from partial measurements with deep delay autoencoders Mason McCallum February 6, 2024
Discovering governing equations from partial measurements with deep delay autoencoders Mason McCallum February 13, 2024
A Machine Learning Framework for Solving High-Dimensional Mean Field Game and Mean Field Control Problems Jimmie Adriazola February 27, 2024
A Mean-Field Games Laboratory for Generative Modeling Jimmie Adriazola March 5, 2024
TBD TBD March 19, 2024
TBD TBD March 26, 2024
Some observations on high-dimensional partial differential equations with Barron data Jimmie Adriazola April 9, 2024
TBD TBD April 16, 2024

Suggested Future Readings:

What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory

Solving high-dimensional partial differential equations using deep learning

Score-Based Generative Modeling through Stochastic Differential Equations

In-context operator learning with data prompts for differential equation problems

Approximation rates for neural networks with general activation functions