Polya-Gamma Augmentation
Data augmentation using Polya-Gamma latent variables.
Description
This method applies Polya-Gamma latent variables as a way to obtain closed form expressions for full-conditionals of posterior distributions in sampling algorithms like MCMC.
Papers Using This Method
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning2021-02-15Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes2020-07-20Mutually Regressive Point Processes2019-12-01PG-TS: Improved Thompson Sampling for Logistic Contextual Bandits2018-05-18Efficient Gaussian Process Classification Using Polya-Gamma Data Augmentation2018-02-18Bayesian inference for logistic models using Polya-Gamma latent variables2012-05-02