270 citations · 1.4k across the 97 of their papers we have counts for
6 papers · 1 filter
Annealed Importance Sampling with q-Paths
Rob Brekelmans, Vaden Masrani, Thang Bui +4
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distribution…
Compressing Deep Neural Networks via Layer Fusion
James O' Neill, Greg Ver Steeg, Aram Galstyan
This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional a…
Robust Classification under Class-Dependent Domain Shift
Tigran Galstyan, Hrant Khachatrian, Greg Ver Steeg +1
Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research. In this paper we explore a special type of…
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
Rob Brekelmans, Vaden Masrani, Frank Wood +2
The recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a family of variational inference objectives, which both tighten and…
Overview of Scanner Invariant Representations
Daniel Moyer, Greg Ver Steeg, Paul M. Thompson
Pooled imaging data from multiple sources is subject to bias from each source. Studies that do not correct for these scanner/site biases at best lose statistical power, and at wors…
Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
Hrayr Harutyunyan, Kyle Reing, Greg Ver Steeg +1
In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise. Standard regularization techniques such as drop…