ML for Scientists: L12
Carol(ina) Cuesta-Lazaro
This week in AI4Science
Autoregressive in Frequency
["CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching" Kannan, Qiu, Cuesta-Lazaro, Jeong (in prep)]
Mean relative velocity
k Nearest neighbours
Pair separation
Pair separation
Varying cosmological parameters
Physics as a testing ground: Well-understood summary statistics enable rigorous validation of generative models
Reproducing summary statistics
\mathrm{R} \sim p(\theta|x)
\mathrm{F} \sim \hat{p}(\theta|x)
Real or Fake?
How good is my generative model?
["A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science" Bischoff et al 2024
arXiv:2403.12636]
Has my model learned the underlying density?
["Generalization in diffusion models arises from geometry-adaptive harmonic representations" Kadkhodaie et al (2024)]
Split training set into non-overlapping
S_1, S_2
https://parti.research.google
A portrait photo of a kangaroo wearing an orange hoodie and blue sunglasses standing on the grass in front of the Sydney Opera House holding a sign on the chest that says Welcome Friends!
Money plot - Nov 18th -> Discuss in class Nov 19th
Transformer from scratch - Nov 4th
Nov 5th discuss in class
Interpretability with Sebastian Oct 29th
Copy of Copy of Copy of Copy of Copy of ML For Scientists: L12
By carol cuesta
