156 citations · 367 across the 18 of their papers we have counts for
10 papers · 1 filter
Multiple Domain Causal Networks
Tianhui Zhou, William E. Carson, Michael Hunter Klein +1
Observational studies are regarded as economic alternatives to randomized trials, often used in their stead to investigate and determine treatment efficacy. Due to lack of sample s…
AugmentedPCA: A Python Package of Supervised and Adversarial Linear Factor Models
William E. Carson, Austin Talbot, David Carlson
Deep autoencoders are often extended with a supervised or adversarial loss to learn latent representations with desirable properties, such as greater predictivity of labels and out…
Supervising the Decoder of Variational Autoencoders to Improve Scientific Utility
Liyun Tu, Austin Talbot, Neil Gallagher +1
Probabilistic generative models are attractive for scientific modeling because their inferred parameters can be used to generate hypotheses and design experiments. This requires th…
Estimating a Brain Network Predictive of Stress and Genotype with Supervised Autoencoders
Austin Talbot, David Dunson, Kafui Dzirasa +1
Targeted stimulation of the brain has the potential to treat mental illnesses. We propose an approach to help design the stimulation protocol by identifying electrical dynamics acr…
On Target Shift in Adversarial Domain Adaptation
Yitong Li, Michael Murias, Samantha Major +2
Discrepancy between training and testing domains is a fundamental problem in the generalization of machine learning techniques. Recently, several approaches have been proposed to l…
Partition Functions from Rao-Blackwellized Tempered Sampling
David Carlson, Patrick Stinson, Ari Pakman +1
Partition functions of probability distributions are important quantities for model evaluation and comparisons. We present a new method to compute partition functions of complex an…
Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
Chunyuan Li, Changyou Chen, David Carlson +1
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods addre…
Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
Changyou Chen, David Carlson, Zhe Gan +2
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) methods are Bayesian analogs to popular stochastic optimization methods; however, this connection is not well studied. We exp…
Neuroprosthetic decoder training as imitation learning
Josh Merel, David Carlson, Liam Paninski +1
Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In…
Deep Temporal Sigmoid Belief Networks for Sequence Modeling
Zhe Gan, Chunyuan Li, Ricardo Henao +2
Deep dynamic generative models are developed to learn sequential dependencies in time-series data. The multi-layered model is designed by constructing a hierarchy of temporal sigmo…