| Date | Speaker | Title |
| January 24, 2019 | Noam Brown | Superhuman AI for heads-up no-limit poker: Libratus beats top professionals |
| February 5, 2019 | Aditya Mishra | Low-rank and sparse structure in modeling multivariate outcome |
| February 26, 2019 | Peter Battaglia | Learning structured models of physics
|
| March 14, 2019 | Leslie Greengard | Fast multipole methods |
| April 2, 2019 | Bin Yu | Three principles of data science: predictability, computability, and stability (PCS)
|
| April 4, 2019 | Miles Stoudenmire | Tensor Networks for Machine Learning
|
| April 24, 2019 | Yashar Hezaveh | Estimating the uncertainties of neural networks predictions
|
| May 30, 2019 | Charles Windolf | Neural Computations via Capsules
|
| June 20, 2019 | Giacomo Torlai | Reconstructing quantum states with Boltzmann machines |
| October 24, 2019 | Miles Cranmer | Introduction to Hamiltonian Neural Networks |
| November 7, 2019 | Dan Foreman-Mackey | Overview of Gaussian Processes for scientific computing |
| November 21, 2019 | Erik Henning Thiede | Group theory for machine learning in the presence of symmetry
|