Starter materials and tutorials for the 2024 IAIFI Astro ML Hackathon.
Facilitator: Carol Cuesta-Lazaro
Understand the generative model paradigm, and learn how to train diffusion generative models for a dataset of your choosing. Explore their utility for emulation, likelihood evaluation, posterior estimation, and anomaly detection.
Repository for starter material
Facilitator: Siddharth Mishra-Sharma
Build up the tools necessary to do simulation-based (or likelihood-free) inference. If you have a forward model or simulator for your data and are sick of losing information by using summary statistics, this may be for you!
Repository for starter material
Facilitators: Siddharth Mishra-Sharma and Alex Gagliano
Understand how to train joint embeddings across or within modalities in a self-supervised or weakly-supervised manner. Examples: (1) images + spectra + light curves, or (2) the same object observed by different instruments. Explore the structure of joint embeddings and how to use them for various downstream tasks. Bring your own multi-modal datasets!
Repository for starter material
Facilitators: Alex Gagliano and Daniel Muthukrishna
Extract informative features and build lower-dimensional representations of your dataset to find the rarest and strangest instances! We’ll hack models for zero-shot and few-shot learning.
Repository for starter material
Facilitator: Yueying Ni
Enhance the resolution of simulations that are too expensive to run at high resolution. Or enhance the resolution of galaxy images for the real observations. Also welcome to bring your own datasets for super resolution!
Repository for starter material
See here for instructions on how to access reserved GPU resources on the Pittsburgh Supercomputing Center's Bridges-2 cluster.