
Explaining Time Series Predictions with Dynamic Masks
How can we explain the predictions of a machine learning model? When the...
read it

The MedkitLearn(ing) Environment: Medical Decision Modelling through Simulation
Understanding decisionmaking in clinical environments is of paramount i...
read it

On Inductive Biases for Heterogeneous Treatment Effect Estimation
We investigate how to exploit structural similarities of an individual's...
read it

Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression
Modeling a system's temporal behaviour in reaction to external stimuli i...
read it

Consistency of mechanistic causal discovery in continuoustime using Neural ODEs
The discovery of causal mechanisms from time series data is a key proble...
read it

Deconfounded Score Method: Scoring DAGs with Dense Unobserved Confounding
Unobserved confounding is one of the greatest challenges for causal disc...
read it

ModelAttentive Ensemble Learning for Sequence Modeling
Medical timeseries datasets have unique characteristics that make predi...
read it

How Faithful is your Synthetic Data? Samplelevel Metrics for Evaluating and Auditing Generative Models
Devising domain and modelagnostic evaluation metrics for generative mo...
read it

Scalable Bayesian Inverse Reinforcement Learning
Bayesian inference over the reward presents an ideal solution to the ill...
read it

Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge
Selecting causal inference models for estimating individualized treatmen...
read it

A Variational Information Bottleneck Approach to MultiOmics Data Integration
Integration of data from multiple omics techniques is becoming increasin...
read it

Policy Analysis using Synthetic Controls in ContinuousTime
Counterfactual estimation using synthetic controls is one of the most su...
read it

Learning Matching Representations for Individualized Organ Transplantation Allocation
Organ transplantation is often the last resort for treating endstage il...
read it

SDFBayes: Cautious Optimism in Safe DoseFinding Clinical Trials with Drug Combinations and Heterogeneous Patient Groups
Phase I clinical trials are designed to test the safety (nontoxicity) o...
read it

Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms
The need to evaluate treatment effectiveness is ubiquitous in most of em...
read it

Personalized Education in the AI Era: What to Expect Next?
The objective of personalized learning is to design an effective knowled...
read it

Synthetic Data: Opening the data floodgates to enable faster, more directed development of machine learning methods
Many groundbreaking advancements in machine learning can be attributed ...
read it

Learning outside the BlackBox: The pursuit of interpretable models
Machine Learning has proved its ability to produce accurate models but t...
read it

CASTLE: Regularization via Auxiliary Causal Graph Discovery
Regularization improves generalization of supervised models to outofsa...
read it

Semiparametric Estimation and Inference on Structural Target Functions using Machine Learning and Influence Functions
We aim to construct a class of learning algorithms that are of practical...
read it

CPAS: the UK's National Machine Learningbased Hospital Capacity Planning System for COVID19
The coronavirus disease 2019 (COVID19) global pandemic poses the threat...
read it

HideandSeek Privacy Challenge
The clinical timeseries setting poses a unique combination of challenge...
read it

Generalization and Invariances in the Presence of Unobserved Confounding
The ability to extrapolate, or generalize, from observed to new related ...
read it

Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift
Modern neural networks have proven to be powerful function approximators...
read it

Strictly Batch Imitation Learning by Energybased Distribution Matching
Consider learning a policy purely on the basis of demonstrated behavior—...
read it

Inverse Active Sensing: Modeling and Understanding Timely DecisionMaking
Evidencebased decisionmaking entails collecting (costly) observations ...
read it

AutoNCP: Automated pipelines for accurate confidence intervals
Successful application of machine learning models to realworld predicti...
read it

Frequentist Uncertainty in Recurrent Neural Networks via Blockwise Influence Functions
Recurrent neural networks (RNNs) are instrumental in modelling sequentia...
read it

Temporal Phenotyping using Deep Predictive Clustering of Disease Progression
Due to the wider availability of modern electronic health records, patie...
read it

Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification
Subgroup analysis of treatment effects plays an important role in applic...
read it

Learning for Dose Allocation in Adaptive Clinical Trials with Safety Constraints
Phase I dosefinding trials are increasingly challenging as the relation...
read it

When and How to Lift the Lockdown? Global COVID19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes
The coronavirus disease 2019 (COVID19) global pandemic has led many cou...
read it

When to Lift the Lockdown? Global COVID19 Scenario Planning and Policy Effects using Compartmental Gaussian Processes
The coronavirus disease 2019 (COVID19) outbreak has led government offi...
read it

A primer on coupled stateswitching models for multiple interacting time series
Stateswitching models such as hidden Markov models or Markovswitching ...
read it

Estimating the Effects of Continuousvalued Interventions using Generative Adversarial Networks
While much attention has been given to the problem of estimating the eff...
read it

Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations
Identifying when to give treatments to patients and how to select among ...
read it

TargetEmbedding Autoencoders for Supervised Representation Learning
Autoencoderbased learning has emerged as a staple for disciplining repr...
read it

Learning Overlapping Representations for the Estimation of Individualized Treatment Effects
The choice of making an intervention depends on its potential benefit or...
read it

Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning
An essential problem in automated machine learning (AutoML) is that of m...
read it

Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes
Comorbid diseases cooccur and progress via complex temporal patterns th...
read it

Contextual Constrained Learning for DoseFinding Clinical Trials
Clinical trials in the medical domain are constrained by budgets. The nu...
read it

A Bayesian Approach to Modelling Longitudinal Data in Electronic Health Records
Analyzing electronic health records (EHR) poses significant challenges b...
read it

Improving Model Robustness Using Causal Knowledge
For decades, researchers in fields, such as the natural and social scien...
read it

A Robust TwoSample Test for Time Series data
We develop a general framework for hypothesis testing with time series d...
read it

Conditional Independence Testing using Generative Adversarial Networks
We consider the hypothesis testing problem of detecting conditional depe...
read it

ASAC: Active Sensing using ActorCritic models
Deciding what and when to observe is critical when making observations i...
read it

Lifelong Bayesian Optimization
Automatic Machine Learning (AutoML) systems tackle the problem of autom...
read it

Machine Learning in the Air
Thanks to the recent advances in processing speed and data acquisition a...
read it

Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders
The estimation of treatment effects is a pervasive problem in medicine. ...
read it

Distributed Task Management in CyberPhysical Systems: How to Cooperate under Uncertainty?
We consider the problem of task allocation in a network of cyberphysica...
read it