274 citations · 389 across the 18 of their papers we have counts for
11 papers · 1 filter
Chain of Log-Concave Markov Chains
Saeed Saremi, Ji Won Park, Francis Bach
We introduce a theoretical framework for sampling from unnormalized densities based on a smoothing scheme that uses an isotropic Gaussian kernel with a single fixed noise scale. We…
Universal Smoothed Score Functions for Generative Modeling
Saeed Saremi, Rupesh Kumar Srivastava, Francis Bach
We consider the problem of generative modeling based on smoothing an unknown density of interest in using factorial kernels with independent Gaussian channels wi…
Multimeasurement Generative Models
Saeed Saremi, Rupesh Kumar Srivastava
We formally map the problem of sampling from an unknown distribution with a density in to the problem of learning and sampling a smoother density in $\mathbb{R}^{Md}…
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…
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+…
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…
On approximating with neural networks
Saeed Saremi
Consider a feedforward neural network such that , where is a smooth function, t…
Neural Empirical Bayes
Saeed Saremi, Aapo Hyvarinen
We unify and and address a set of problems in unsupervised learning with a geometric interpretation of those methods…
Deep Energy Estimator Networks
Saeed Saremi, Arash Mehrjou, Bernhard Schölkopf +1
Density estimation is a fundamental problem in statistical learning. This problem is especially challenging for complex high-dimensional data due to the curse of dimensionality. A…
Annealed Generative Adversarial Networks
Arash Mehrjou, Bernhard Schölkopf, Saeed Saremi
We introduce a novel framework for adversarial training where the target distribution is annealed between the uniform distribution and the data distribution. We posited a conjectur…
The Wilson Machine for Image Modeling
Saeed Saremi, Terrence J. Sejnowski
Learning the distribution of natural images is one of the hardest and most important problems in machine learning. The problem remains open, because the enormous complexity of the…