22 citations · 33 across the 6 of their papers we have counts for
6 papers
Utility Theory for Sequential Decision Making
Mehran Shakerinava, Siamak Ravanbakhsh
The von Neumann-Morgenstern (VNM) utility theorem shows that under certain axioms of rationality, decision-making is reduced to maximizing the expectation of some utility function.…
Annealing Gaussian into ReLU: a New Sampling Strategy for Leaky-ReLU RBM
Chun-Liang Li, Siamak Ravanbakhsh, Barnabas Poczos
Restricted Boltzmann Machine (RBM) is a bipartite graphical model that is used as the building block in energy-based deep generative models. Due to numerical stability and quantifi…
Deep Learning with Sets and Point Clouds
Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos
We introduce a simple permutation equivariant layer for deep learning with set structure.This type of layer, obtained by parameter-sharing, has a simple implementation and linear-t…
Revisiting Algebra and Complexity of Inference in Graphical Models
Siamak Ravanbakhsh, Russell Greiner
This paper studies the form and complexity of inference in graphical models using the abstraction offered by algebraic structures. In particular, we broadly formalize inference pro…
Training Restricted Boltzmann Machine by Perturbation
Siamak Ravanbakhsh, Russell Greiner, Brendan Frey
A new approach to maximum likelihood learning of discrete graphical models and RBM in particular is introduced. Our method, Perturb and Descend (PD) is inspired by two ideas (I) pe…
A Generalized Loop Correction Method for Approximate Inference in Graphical Models
Siamak Ravanbakhsh, Chun-Nam Yu, Russell Greiner
Belief Propagation (BP) is one of the most popular methods for inference in probabilistic graphical models. BP is guaranteed to return the correct answer for tree structures, but c…