Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Quasi Monte Carlo methods enable extremely low-dimensional deep generative models
Miles Martinez, Alex H. Williams
This paper introduces quasi-Monte Carlo latent variable models (QLVMs): a class of deep generative models that are specialized for finding extremely low-dimensional and interpretab…
cs.LG2022
Reproducible, incremental representation learning with Rosetta VAE
Miles Martinez, John Pearson
Variational autoencoders are among the most popular methods for distilling low-dimensional structure from high-dimensional data, making them increasingly valuable as tools for data…