Papers

Semi-Supervised Multimodal Multi-Instance Learning for Aortic Stenosis Diagnosis

Zhe Huang, Xiaowei Yu, Benjamin S. Wessler, Michael C. Hughes

Decision-aware training of spatiotemporal forecasting models to select a top K subset of sites for intervention

Kyle Heuton, F. Samuel Muench, Shikhar Shrestha, Thomas Stopka, and Michael C. Hughes

Learning Hyperparameters via a Data-Emphasized Variational Objective

Ethan Harvey, Mikhail Petrov, and Michael C. Hughes

Using machine learning to measure evidence of students' sensemaking in physics courses

Kaitlin Gili, Kyle Heuton, Astha Shah, and Michael C. Hughes

Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective

Ethan Harvey, Mikhail Petrov, and Michael C. Hughes

Validation of System for Automated Screening for Aortic Stenosis

Samuel Karmiy, Zhe Huang, Eileen Mai, Jing Li, Monica Dehn, Davinder Ramsingh, John Martin, Ayan R. Patel, Michael C. Hughes, and Benjamin S. Wessler

Spatiotemporal Forecasting of Opioid-related Fatal Overdoses: Towards Best Practices for Modeling and Evaluation

SINCERE: Supervised Information Noise-Contrastive Estimation REvisited

Patrick Feeney and Michael C. Hughes

Discovering group dynamics in coordinated time series via hierarchical recurrent switching-state models

Michael T. Wojnowicz, Kaitlin Gili, Preetish Rath, Eric Miller, Jeffrey Miller, Clifford Hancock, Meghan O'Donovan, Seth Elkin-Frankston, Tad T. Brunyé, and Michael C. Hughes

InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning

Systematic comparison of semi-supervised and self-supervised learning for medical image classification

Transfer Learning with Informative Priors: Simple Baselines Better than Previously Reported

A Neurosymbolic Cognitive Architecture Framework for Handling Novelties in Open Worlds

A Probabilistic Method to Predict Classifier Accuracy on Larger Datasets given Small Pilot Data

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning

Non-Parametric and Regularized Dynamical Wasserstein Barycenters for Sequential Observations

Approximate inference by broadening the support of the likelihood

Learning where to intervene with a differentiable top-k operator: Towards data-driven strategies to prevent fatal opioid overdoses

Semi-supervised Ordinal Regression via Cumulative Link Models for Predicting In-Hospital Length-of-Stay

NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds

Fix-A-Step: Semi-supervised Learning from Uncurated Unlabeled Data

Automated Detection of Aortic Stenosis using Machine Learning

Predicting Spatiotemporal Counts of Opioid-related Fatal Overdoses via Zero-Inflated Gaussian Processes

Semi-supervised Learning from Uncurated Echocardiogram Images with Fix-A-Step

Prediction-Constrained Markov Models for Medical Time Series with Missing Data and Few Labels

Easy Variational Inference for Categorical Models via an Independent Binary Approximation

TMED 2: A Dataset for Semi-Supervised Classification of Echocardiograms

Optimizing Early Warning Classifiers to Control False Alarms via a Minimum Precision Constraint

Learning Consistent Deep Generative Models from Sparsely Labeled Data

Dynamical Wasserstein Barycenters for Time-series Modeling

The Tufts fNIRS Mental Workload Dataset & Benchmark for Brain-Computer Interfaces that Generalize

A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms

Zhe Huang, Gary Long, Benjamin Wessler, and Michael C. Hughes

Machine Learning for Healthcare (MLHC)

Approximate Bayesian Computation for an Explicit-Duration Hidden Markov Model of COVID-19 Hospital Trajectories

Gian Marco Visani, Alexandra Hope Lee, Cuong Nguyen, David M. Kent, John B. Wong, Joshua T. Cohen, and Michael C. Hughes

Machine Learning for Healthcare (MLHC)

Taming fNIRS-based BCI Input for Beter Calibration and Broader Use

Liang Wang, Zhe Huang, Ziyu Zhou, Devon McKeon, Giles Blaney, Michael C. Hughes, and Robert J. K. Jacob

ACM Symposium on User Interface Software and Technology (UIST), 2021

Easy Variational Inference for Categorical Observations via a New View of Diagonal Orthant Probit Models

Michael T. Wojnowicz, Shuchin Aeron, Eric L. Miller, and Michael C. Hughes

Tractable Probabilistic Modeling workshop at UAI 2021

Stochastic Iterative Graph Matching

Linfeng Liu, Michael C. Hughes, Soha Hassoun, and Liping Liu

International Conference on Machine Learning (ICML), 2021

Evaluating the Use of Reconstruction Error for Novelty Localization

Patrick Feeney and Michael C. Hughes

Uncertainty and Robustness in Deep Learning (UDL) workshop at ICML 2021

Prediction-Constrained Hidden Markov Models for Semi-Supervised Classification

Gabriel Hope, Michael C. Hughes, Finale Doshi-Velez, and Erik Sudderth

Time Series Workshop at ICML 2021

Forecasting COVID-19 Counts At A Single Hospital: A Hierarchical Bayesian Approach

Alexandra Hope Lee, Panagiotis Lymperopoulos, Joshua T. Cohen, John B. Wong, and Michael C. Hughes

Enzyme Promiscuity Prediction Using Hierarchy-Informed Multi-Label Classification

Gian Marco Visani, Michael C. Hughes, and Soha Hassoun

Modeling Graph Node Correlations with Neighbor Mixture Models

Linfeng Liu, Michael C. Hughes, and Liping Liu

Assessment of a Prediction Model for Antidepressant Treatment Stability Using Supervised Topic Models

Michael C. Hughes, Melanie F. Pradier, Andrew Slavin Ross, Thomas H. McCoy Jr, Roy H. Perlis, Finale Doshi-Velez

MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III

Shirly Wang, Matthew B. A. McDermott, Geeticka Chauhan, Marzyeh Ghassemi, Michael C. Hughes, and Tristan Naumann

POPCORN: Partially Observed Prediction-Constrained Reinforcement Learning

Joseph Futoma, Michael C. Hughes, and Finale Doshi-Velez"

On Matched Filtering for Statistical Change Point Detection

Kevin C. Cheng, Eric L. Miller, Michael C. Hughes, and Shuchin Aeron

Optimal Transport Based Change Point Detection and Time Series Clustering

Kevin C. Cheng, Shuchin Aeron, Michael C. Hughes, Erika Hussey, and Eric L. Miller

Regional Tree Regularization for Interpretability in Deep Neural Networks

Mike Wu, Sonali Parbhoo, Michael C. Hughes, Ryan Kindle, Leo Celi, Maurizio Zazzi, Volker Roth, and Finale Doshi-Velez

Rapid Model Comparison by Amortizing Across Models

Lily H. Zhang and Michael C. Hughes

Challenges in Computing and Optimizing Upper Bounds of Marginal Likelihood based on Chi-Square Divergences

Melanie F. Pradier, Michael C. Hughes, and Finale Doshi-Velez

Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks

Bret Nestor, Matthew B.A. McDermott, Willie, Boag, Gabriela Berner, Tristan Nauman, Michael C. Hughes, Anna Goldenberg, and Marzyeh Ghassemi

Supervised Machine Learning Algorithms Using Patient Related Factors to Predict in-Hospital Mortality Following Acute Myeloid Leukemia Therapy

Nauman Saleem Siddiqui, Andreas Klein, Amandeep Godara, Cindy Varga, Rachel J. Buchsbaum, and Michael C. Hughes

Sensorimotor Cross-Behavior Knowledge Transfer for Grounded Category Recognition

Gyan Tatiya, Ramtin Hosseini, Michael C. Hughes, and Jivko Sinapov

Prediction-Constrained POMDPs

Joseph Futoma, Michael C. Hughes, and Finale Doshi-Velez

Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation

Bret Nestor, Matthew B. A. McDermott, Geeticka Chauhan, Tristan Naumann, Michael C. Hughes, Anna Goldenberg, Marzyeh Ghassemi

Semi-Supervised Prediction-Constrained Topic Models

Michael C. Hughes, Gabriel Hope, Leah Weiner, Thomas H. McCoy, Jr., Roy H. Perlis, Erik B. Sudderth, and Finale Doshi-Velez

Beyond Sparsity: Tree Regularization of Deep Models for Interpretability

Mike Wu, Michael C. Hughes, Sonali Parbhoo, Maurizio Zazzi, Volker Roth, and Finale Doshi-Velez

Prediction-Constrained Topic Models for Antidepressant Prediction

Michael C. Hughes, Gabriel Hope, Leah Weiner, Thomas H. McCoy, MD, Roy H. Perlis, MD, Erik B. Sudderth, and Finale Doshi-Velez

From Patches to Images: A Nonparametric Generative Model

Geng Ji, Michael C. Hughes, Erik B. Sudderth

Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations

Andrew Slavin Ross, Michael C. Hughes, Finale Doshi-Velez

Predicting intervention onset in the ICU with switching state space models

Marzyeh Ghassemi*, Mike Wu*, Michael C. Hughes*, Peter Szolovits, Finale Doshi-Velez

Refinery: An Open Source Topic Modeling Web Platform

Daeil Kim, Benjamin F. Swanson, Michael C. Hughes, Erik B. Sudderth

JMLR Machine Learning Open Source Software (MLOSS) 2017

Supervised topic models for clinical interpretability

Michael C. Hughes, Huseyin Melih Elibol Thomas McCoy, MD Roy Perlis, MD Finale Doshi-Velez

From Patches to Natural Images via Hierarchical Dirichlet Processes

Geng Ji, Michael C. Hughes, Erik B. Sudderth

Practical Bayesian nonparametrics workshop at NIPS 2016

Fast Learning of Clusters and Topics via Sparse Posteriors

Michael C. Hughes, Erik B. Sudderth

unpublished preprint

Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models

Michael C. Hughes, William Stephenson, Erik B. Sudderth

Neural Information Processing Systems, 2015.

Reliable and Scalable Variational Inference for the Hierarchical Dirichlet Process.

Michael C. Hughes, Daeil Kim, Erik B. Sudderth

Artificial Intelligence & Statistics, 2015.

bnpy: Reliable and scalable variational inference for Bayesian nonparametric models

Joint Modeling of Multiple Time Series via the Beta Process with Application to Motion Capture Segmentation.

Memoized Online Variational Inference for Dirichlet Process Mixture Models

Effective Split-Merge Monte Carlo Methods for Nonparametric Models of Sequential Data

The Nonparametric Metadata Dependent Relational Model

Nonparametric Discovery of Activity Patterns from Video Collections