We develop a Reinforcement Learning (RL) framework for improving an existing behavior policy via sparse, user-interpretable changes.
A precise description of the causal estimand highlights which OPE estimands are identifiable from observational data under the stated generative assumptions.
Probabilistic models help us encode latent structures that both model the data and are ideally also useful for specific downstream tasks.
Machine learning models that utilize patient data across time (rather than just the most recent measurements) have increased performance for many risk stratification tasks in the intensive care unit.
We propose SLTD (`Sequential Learning-to-Defer') a framework for learning-to-defer pre-emptively to an expert in sequential decision-making settings.
Estimating an individual's potential response to interventions from observational data is of high practical relevance for many domains, such as healthcare, public policy or economics.
We propose Preferential MoE, a novel human-ML mixture-of-experts model that augments human expertise in decision making with a data-based classifier only when necessary for predictive performance.
Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with rapid human-to-human transmission and a high case fatality rate particularly in older patients.
Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity.
Moreover, for situations in which a single, global tree is a poor estimator, we introduce a regional tree regularizer that encourages the deep model to resemble a compact, axis-aligned decision tree in predefined, human-interpretable contexts.
The lack of interpretability remains a barrier to the adoption of deep neural networks.
Estimating the causal effects of an intervention in the presence of confounding is a frequently occurring problem in applications such as medicine.
Computer vision tasks are difficult because of the large variability in the data that is induced by changes in light, background, partial occlusion as well as the varying pose, texture, and shape of objects.
Estimating the causal effects of an intervention from high-dimensional observational data is difficult due to the presence of confounding.
The lack of interpretability remains a key barrier to the adoption of deep models in many applications.
In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter.