We are Harvard’s Data to Actionable Knowledge (DtAK) lab, led by Finale Doshi-Velez. We use probabilistic methods to address many decision-making scenarios involving humans and AI. Our work spans specific application domains (health and wellness) as well as broader socio-technical questions around human-AI interaction, AI accountability, and responsible and effective AI regulation. Our work falls into three major areas:
- Probabilistic modeling and inference:
We focus especially on Bayesian models
- How can we characterize the uncertainty in large, heterogeneous data?
- How can we fit models that will be useful for downstream decision-making?
- How can we build models and inference techniques that will behave in expected and desired ways?
- Decision-making under uncertainty:
We focus especially on sequential decision-making
- How can we optimize policies given batches of heterogeneous data?
- How can we provide useful information, even if we can’t solve for a policy?
- How can we characterize the limits of our ability to provide decision support?
- Interpretability and statistical methods for validation:
- How can we estimate the quality of a policy from batch data?
- How can we expose key elements of a model or policy for expert inspection?