
A BayesOptimal View on Adversarial Examples
The ability to fool modern CNN classifiers with tiny perturbations of th...
read it

On GANs and GMMs
A longstanding problem in machine learning is to find unsupervised metho...
read it

Why do deep convolutional networks generalize so poorly to small image transformations?
Deep convolutional network architectures are often assumed to guarantee ...
read it

A Tight Convex Upper Bound on the Likelihood of a Finite Mixture
The likelihood function of a finite mixture model is a nonconvex functi...
read it

Statistics of RGBD Images
Cameras that can measure the depth of each pixel in addition to its colo...
read it

Beyond Brightness Constancy: Learning Noise Models for Optical Flow
Optical flow is typically estimated by minimizing a "data cost" and an o...
read it

Tighter Linear Program Relaxations for High Order Graphical Models
Graphical models with High Order Potentials (HOPs) have received conside...
read it

Loopy Belief Propagation for Approximate Inference: An Empirical Study
Recently, researchers have demonstrated that loopy belief propagation  ...
read it

The Factored Frontier Algorithm for Approximate Inference in DBNs
The Factored Frontier (FF) algorithm is a simple approximate inferenceal...
read it

MAP Estimation, Linear Programming and Belief Propagation with Convex Free Energies
Finding the most probable assignment (MAP) in a general graphical model ...
read it

Tightening LP Relaxations for MAP using Message Passing
Linear Programming (LP) relaxations have become powerful tools for findi...
read it

Convergent message passing algorithms  a unifying view
Messagepassing algorithms have emerged as powerful techniques for appro...
read it
Yair Weiss
is this you? claim profile