274 citations · 389 across the 18 of their papers we have counts for
Showing 2020 · stat.MLShow all
3 papers · 2 filters
stat.ML2020
Unnormalized Variational Bayes
Saeed Saremi
We unify empirical Bayes and variational Bayes for approximating unnormalized densities. This framework, named unnormalized variational Bayes (UVB), is based on formulating a laten…
stat.ML2020★ 1 cited
Learning and Inference in Imaginary Noise Models
Saeed Saremi
Inspired by recent developments in learning smoothed densities with empirical Bayes, we study variational autoencoders with a decoder that is tailored for the random variable $Y=X+…
stat.ML2020★ 2 cited
Provable Robust Classification via Learned Smoothed Densities
Saeed Saremi, Rupesh Srivastava
Smoothing classifiers and probability density functions with Gaussian kernels appear unrelated, but in this work, they are unified for the problem of robust classification. The key…