Daniel Jarrett
YOU?
Author Swipe
View article: Time-series Generation by Contrastive Imitation
Time-series Generation by Contrastive Imitation Open
Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepwise) transitions, but its open-loop rollouts should also pr…
View article: Invariant Causal Imitation Learning for Generalizable Policies
Invariant Causal Imitation Learning for Generalizable Policies Open
Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be different, directly lea…
View article: Inverse Decision Modeling: Learning Interpretable Representations of Behavior
Inverse Decision Modeling: Learning Interpretable Representations of Behavior Open
Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…
View article: Online Decision Mediation
Online Decision Mediation Open
Consider learning a decision support assistant to serve as an intermediary between (oracle) expert behavior and (imperfect) human behavior: At each time, the algorithm observes an action chosen by a fallible agent, and decides whether to *…
View article: Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning
Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning Open
Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker's policy is challenging -- with no acce…
View article: Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples
Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples Open
Learning controllers with offline data in decision-making systems is an essential area of research due to its potential to reduce the risk of applications in real-world systems. However, in responsibility-sensitive settings such as healthc…
View article: Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments
Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments Open
Consider the problem of exploration in sparse-reward or reward-free environments, such as in Montezuma's Revenge. In the curiosity-driven paradigm, the agent is rewarded for how much each realized outcome differs from their predicted outco…
View article: HyperImpute: Generalized Iterative Imputation with Automatic Model Selection
HyperImpute: Generalized Iterative Imputation with Automatic Model Selection Open
Consider the problem of imputing missing values in a dataset. One the one hand, conventional approaches using iterative imputation benefit from the simplicity and customizability of learning conditional distributions directly, but suffer f…
View article: Inverse Contextual Bandits: Learning How Behavior Evolves over Time
Inverse Contextual Bandits: Learning How Behavior Evolves over Time Open
Understanding a decision-maker's priorities by observing their behavior is critical for transparency and accountability in decision processes, such as in healthcare. Though conventional approaches to policy learning almost invariably assum…
View article: The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation Open
Understanding decision-making in clinical environments is of paramount importance if we are to bring the strengths of machine learning to ultimately improve patient outcomes. Several factors including the availability of public data, the i…
View article: Clairvoyance: A Pipeline Toolkit for Medical Time Series.
Clairvoyance: A Pipeline Toolkit for Medical Time Series. Open
Time-series learning is the bread and butter of data-driven *clinical decision support*, and the recent explosion in ML research has demonstrated great potential in various healthcare settings. At the same time, medical time-series problem…
View article: Hide-and-Seek Privacy Challenge
Hide-and-Seek Privacy Challenge Open
The clinical time-series setting poses a unique combination of challenges to data modeling and sharing. Due to the high dimensionality of clinical time series, adequate de-identification to preserve privacy while retaining data utility is …
View article: Batch Inverse Reinforcement Learning Using Counterfactuals for Understanding Decision Making.
Batch Inverse Reinforcement Learning Using Counterfactuals for Understanding Decision Making. Open
A key challenge in modeling real-world decision-making is the fact that active experimentation is often impossible (e.g. in healthcare). The goal of batch inverse reinforcement learning is to recover and understand policies on the basis of…
View article: Learning "What-if" Explanations for Sequential Decision-Making
Learning "What-if" Explanations for Sequential Decision-Making Open
Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i.e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- is essential for int…
View article: Inverse Active Sensing: Modeling and Understanding Timely Decision-Making
Inverse Active Sensing: Modeling and Understanding Timely Decision-Making Open
Evidence-based decision-making entails collecting (costly) observations about an underlying phenomenon of interest, and subsequently committing to an (informed) decision on the basis of accumulated evidence. In this setting, active sensing…
View article: Strictly Batch Imitation Learning by Energy-based Distribution Matching
Strictly Batch Imitation Learning by Energy-based Distribution Matching Open
Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch imitati…
View article: Inverse Active Sensing: Modeling and Understanding Timely\n Decision-Making
Inverse Active Sensing: Modeling and Understanding Timely\n Decision-Making Open
Evidence-based decision-making entails collecting (costly) observations about\nan underlying phenomenon of interest, and subsequently committing to an\n(informed) decision on the basis of accumulated evidence. In this setting,\nactive sens…
View article: Target-Embedding Autoencoders for Supervised Representation Learning
Target-Embedding Autoencoders for Supervised Representation Learning Open
Autoencoder-based learning has emerged as a staple for disciplining representations in unsupervised and semi-supervised settings. This paper analyzes a framework for improving generalization in a purely supervised setting, where the target…
View article: Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning
Stepwise Model Selection for Sequence Prediction via Deep Kernel Learning Open
An essential problem in automated machine learning (AutoML) is that of model selection. A unique challenge in the sequential setting is the fact that the optimal model itself may vary over time, depending on the distribution of features an…
View article: Applications and limitations of machine learning in radiation oncology
Applications and limitations of machine learning in radiation oncology Open
Machine learning approaches to problem-solving are growing rapidly within healthcare, and radiation oncology is no exception. With the burgeoning interest in machine learning comes the significant risk of misaligned expectations as to what…
View article: MATCH-Net: Dynamic Prediction in Survival Analysis using Convolutional Neural Networks
MATCH-Net: Dynamic Prediction in Survival Analysis using Convolutional Neural Networks Open
Accurate prediction of disease trajectories is critical for early identification and timely treatment of patients at risk. Conventional methods in survival analysis are often constrained by strong parametric assumptions and limited in thei…