270 citations · 1.4k across the 97 of their papers we have counts for
6 papers · 1 filter
Measures of Tractography Convergence
Daniel Moyer, Paul M. Thompson, Greg Ver Steeg
In the present work, we use information theory to understand the empirical convergence rate of tractography, a widely-used approach to reconstruct anatomical fiber pathways in the…
A Forest Mixture Bound for Block-Free Parallel Inference
Neal Lawton, Aram Galstyan, Greg Ver Steeg
Coordinate ascent variational inference is an important algorithm for inference in probabilistic models, but it is slow because it updates only a single variable at a time. Block c…
Invariant Representations without Adversarial Training
Daniel Moyer, Shuyang Gao, Rob Brekelmans +2
Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling th…
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
Sahil Garg, Irina Rish, Guillermo Cecchi +5
We propose a novel dialogue modeling framework, the first-ever nonparametric kernel functions based approach for dialogue modeling, which learns kernelized hashcodes as compressed…
Auto-Encoding Total Correlation Explanation
Shuyang Gao, Rob Brekelmans, Greg Ver Steeg +1
Advances in unsupervised learning enable reconstruction and generation of samples from complex distributions, but this success is marred by the inscrutability of the representation…
Stochastic Learning of Nonstationary Kernels for Natural Language Modeling
Sahil Garg, Greg Ver Steeg, Aram Galstyan
Natural language processing often involves computations with semantic or syntactic graphs to facilitate sophisticated reasoning based on structural relationships. While convolution…