The lack of interpretability remains a key barrier to the adoption of deep models in many
applications. In this work, we explicitly regularize deep models so human users might step …

Abstract Concept bottleneck models (CBMs) enhance the interpretability of their predictions
by first predicting high-level concepts given features, and subsequently predicting outcomes …

The HIV-1 reservoir is the major hurdle to a cure. We here evaluate viral and host
characteristics associated with reservoir size and long-term dynamics in 1,057 individuals …

Abstract Coronavirus disease 2019 (COVID-19) is a respiratory disease with rapid human-to-
human transmission caused by the severe acute respiratory syndrome coronavirus 2 (SARS …

We present a mixture-of-experts approach for HIV therapy selection. The heterogeneity in
patient data makes it difficult for one particular model to succeed at providing suitable …

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 …

Discount regularization, using a shorter planning horizon when calculating the optimal
policy, is a popular choice to restrict planning to a less complex set of policies when …

The lack of interpretability remains a barrier to adopting deep neural networks across many
safety-critical domains. Tree regularization was recently proposed to encourage a deep …

Deep models have advanced prediction in many domains, but their lack of interpretability
remains a key barrier to the adoption in many real world applications. There exists a large …

Abstract 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 …