23 citations · 39 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2012★ 2 cited
Efficient Methods for Unsupervised Learning of Probabilistic Models
Jascha Sohl-Dickstein
In this thesis I develop a variety of techniques to train, evaluate, and sample from intractable and high dimensional probabilistic models. Abstract exceeds arXiv space limitations…
cs.LG2012★ 23 cited
Hamiltonian Annealed Importance Sampling for partition function estimation
Jascha Sohl-Dickstein, Benjamin J. Culpepper
We introduce an extension to annealed importance sampling that uses Hamiltonian dynamics to rapidly estimate normalization constants. We demonstrate this method by computing log li…
cs.LG2012★ 7 cited
The Natural Gradient by Analogy to Signal Whitening, and Recipes and Tricks for its Use
Jascha Sohl-Dickstein
The natural gradient allows for more efficient gradient descent by removing dependencies and biases inherent in a function's parameterization. Several papers present the topic thor…