2 papers
stat.ML2019
Approximate Inference Turns Deep Networks into Gaussian Processes
Mohammad Emtiyaz Khan, Alexander Immer, Ehsan Abedi +1
Deep neural networks (DNN) and Gaussian processes (GP) are two powerful models with several theoretical connections relating them, but the relationship between their training metho…
math.OC2019
Gauge Freedom within the Class of Linear Feedback Particle Filters
Ehsan Abedi, Simone Carlo Surace
Feedback particle filters (FPFs) are Monte-Carlo approximations of the solution of the filtering problem in continuous time. The samples or particles evolve according to a feedback…