Events

CS Colloquium: An algorithmic safety view of learning in healthcare

Speaker: Shalmali Joshi

Location: On-Line
Videoconference link: https://nyu.zoom.us/j/91217781020

Date: Wednesday, March 9, 2022

Machine Learning advances have revolutionized many domains
such as machine translation, complex game playing, and scientific
discovery. On the other hand, ML has only enjoyed modest successes in
healthcare. To improve the utility, reliability, and robustness of
Machine Learning (ML) models in human-centered domains such as health,
we need to address several foundational challenges. In this talk, I will
demonstrate how an algorithmic-safety perspective can motivate specific
technical challenges for learning in healthcare. Specifically, I will
discuss the need to improve the utility of ML-robustness, explainability
with an emphasis on decision-making, and post-hoc algorithmic safety to
prevent harm. I will discuss my contributions on i) aiding safe
decision-making in non-IID settings using time-series explainability
intended to address clinicians’ requirements, ii) novel learning
algorithms to optimize for safety in sequential decision-making
settings, and iii) methods to improve causal robustness of ML methods
designed for practical generative settings. I will conclude with an
overview of my future research vision on designing novel objectives for
expanding ML-based solutions to general and practical generative
settings we encounter in health and outlining an experimental design
framework for validating ML models targeting these objectives.