1.4k citations · 8.8k across the 91 of their papers we have counts for
6 papers · 1 filter
Minimum and maximum entropy distributions for binary systems with known means and pairwise correlations
Badr F. Albanna, Christopher Hillar, Jascha Sohl-Dickstein +1
Maximum entropy models are increasingly being used to describe the collective activity of neural populations with measured mean neural activities and pairwise correlations, but the…
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…
Hamiltonian Monte Carlo with Reduced Momentum Flips
Jascha Sohl-Dickstein
Hamiltonian Monte Carlo (or hybrid Monte Carlo) with partial momentum refreshment explores the state space more slowly than it otherwise would due to the momentum reversals which o…
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…
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…
Efficient and optimal binary Hopfield associative memory storage using minimum probability flow
Christopher Hillar, Jascha Sohl-Dickstein, Kilian Koepsell
We present an algorithm to store binary memories in a Hopfield neural network using minimum probability flow, a recent technique to fit parameters in energy-based probabilistic mod…