140 citations · 341 across the 21 of their papers we have counts for
24 papers
On the Impact of Random Seeds on the Fairness of Clinical Classifiers
Silvio Amir, Jan-Willem van de Meent, Byron C. Wallace
Recent work has shown that fine-tuning large networks is surprisingly sensitive to changes in random seed(s). We explore the implications of this phenomenon for model fairness acro…
Disentangling Representations of Text by Masking Transformers
Xiongyi Zhang, Jan-Willem van de Meent, Byron C. Wallace
Representations from large pretrained models such as BERT encode a range of features into monolithic vectors, affording strong predictive accuracy across a multitude of downstream…
Learning Proposals for Probabilistic Programs with Inference Combinators
Sam Stites, Heiko Zimmermann, Hao Wu +2
We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance sam…
Action Priors for Large Action Spaces in Robotics
Ondrej Biza, Dian Wang, Robert Platt +2
In robotics, it is often not possible to learn useful policies using pure model-free reinforcement learning without significant reward shaping or curriculum learning. As a conseque…
Query-Focused EHR Summarization to Aid Imaging Diagnosis
Denis Jered McInerney, Borna Dabiri, Anne-Sophie Touret +3
Electronic Health Records (EHRs) provide vital contextual information to radiologists and other physicians when making a diagnosis. Unfortunately, because a given patient's record…
Deep Markov Spatio-Temporal Factorization
Amirreza Farnoosh, Behnaz Rezaei, Eli Zachary Sennesh +6
We introduce deep Markov spatio-temporal factorization (DMSTF), a generative model for dynamical analysis of spatio-temporal data. Like other factor analysis methods, DMSTF approxi…
Learning Discrete State Abstractions With Deep Variational Inference
Ondrej Biza, Robert Platt, Jan-Willem van de Meent +1
Abstraction is crucial for effective sequential decision making in domains with large state spaces. In this work, we propose an information bottleneck method for learning approxima…
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
Hao Wu, Heiko Zimmermann, Eli Sennesh +2
We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frames structured variational inference as adaptive importance sampling. APG samplers constru…
Neural Topographic Factor Analysis for fMRI Data
Eli Sennesh, Zulqarnain Khan, Yiyu Wang +4
Neuroimaging studies produce gigabytes of spatio-temporal data for a small number of participants and stimuli. Rarely do researchers attempt to model and examine how individual par…
Structured Neural Topic Models for Reviews
Babak Esmaeili, Hongyi Huang, Byron C. Wallace +1
We present Variational Aspect-based Latent Topic Allocation (VALTA), a family of autoencoding topic models that learn aspect-based representations of reviews. VALTA defines a user-…
Nested Reasoning About Autonomous Agents Using Probabilistic Programs
Iris Rubi Seaman, Jan-Willem van de Meent, David Wingate
As autonomous agents become more ubiquitous, they will eventually have to reason about the plans of other agents, which is known as theory of mind reasoning. We develop a planning-…
Composing Modeling and Inference Operations with Probabilistic Program Combinators
Eli Sennesh, Adam Ścibior, Hao Wu +1
Probabilistic programs with dynamic computation graphs can define measures over sample spaces with unbounded dimensionality, which constitute programmatic analogues to Bayesian non…
On Exploration, Exploitation and Learning in Adaptive Importance Sampling
Xiaoyu Lu, Tom Rainforth, Yuan Zhou +2
We study adaptive importance sampling (AIS) as an online learning problem and argue for the importance of the trade-off between exploration and exploitation in this adaptation. Bor…
An Introduction to Probabilistic Programming
Jan-Willem van de Meent, Brooks Paige, Hongseok Yang +1
This book is a graduate-level introduction to probabilistic programming. It not only provides a thorough background for anyone wishing to use a probabilistic programming system, bu…
Inference Trees: Adaptive Inference with Exploration
Tom Rainforth, Yuan Zhou, Xiaoyu Lu +4
We introduce inference trees (ITs), a new class of inference methods that build on ideas from Monte Carlo tree search to perform adaptive sampling in a manner that balances explora…
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts
Sarthak Jain, Edward Banner, Jan-Willem van de Meent +2
We propose a method for learning disentangled representations of texts that code for distinct and complementary aspects, with the aim of affording efficient model transfer and inte…
Structured Disentangled Representations
Babak Esmaeili, Hao Wu, Sarthak Jain +6
Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disen…
Bayesian Optimization for Probabilistic Programs
Tom Rainforth, Tuan Anh Le, Jan-Willem van de Meent +2
We present the first general purpose framework for marginal maximum a posteriori estimation of probabilistic program variables. By using a series of code transformations, the evide…
Learning Disentangled Representations with Semi-Supervised Deep Generative Models
N. Siddharth, Brooks Paige, Jan-Willem van de Meent +5
Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the dat…
Inducing Interpretable Representations with Variational Autoencoders
N. Siddharth, Brooks Paige, Alban Desmaison +5
We develop a framework for incorporating structured graphical models in the \emph{encoders} of variational autoencoders (VAEs) that allows us to induce interpretable representation…
Interacting Particle Markov Chain Monte Carlo
Tom Rainforth, Christian A. Naesseth, Fredrik Lindsten +4
We introduce interacting particle Markov chain Monte Carlo (iPMCMC), a PMCMC method based on an interacting pool of standard and conditional sequential Monte Carlo samplers. Like r…
A New Approach to Probabilistic Programming Inference
Frank Wood, Jan Willem van de Meent, Vikash Mansinghka
We introduce and demonstrate a new approach to inference in expressive probabilistic programming languages based on particle Markov chain Monte Carlo. Our approach is simple to imp…
Particle Gibbs with Ancestor Sampling for Probabilistic Programs
Jan-Willem van de Meent, Hongseok Yang, Vikash Mansinghka +1
Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference. A drawback of these techniques is that they rely on im…
Tempering by Subsampling
Jan-Willem van de Meent, Brooks Paige, Frank Wood
In this paper we demonstrate that tempering Markov chain Monte Carlo samplers for Bayesian models by recursively subsampling observations without replacement can improve the perfor…