Uncertainty and information for ML-driven decision making

Speaker: Shengjia ZHAO
         Stanford University

Title:   "Uncertainty and information for ML-driven decision making"

Date:    Monday, 21 February 2022

Time:    10:00am - 11:00am (HKT)

Zoom link:
https://hkust.zoom.us/j/928308079?pwd=MW9wTCtlSDd2MnViZGdNd2oreUpXZz09

Meeting ID:     928 308 079
Passcode:       20212022

Abstract:

Prediction models should know what they do not know if they are to be
trusted for making important decisions. Prediction models would accurately
capture their uncertainty if they could predict the true probability of
the outcome of interest, such as the true probability of a patient's
illness given the symptoms. While outputting these probabilities exactly
is impossible in most cases, I show that it is surprisingly possible to
learn probabilities that are "indistinguishable" from the true
probabilities for large classes of decision making tasks. I propose
algorithms to learn indistinguishable probabilities, and show that they
provably enable accurate risk assessment and better decision outcomes. In
addition to learning probabilities that capture uncertainty, my talk will
also discuss how to acquire information to reduce uncertainty in ways that
optimally improve decision making. Empirically, these methods lead to
prediction models that enable better and more confident decision making in
applications such as medical diagnosis and policy making.


*****************
Biography:

Shengjia is a PhD candidate at the Department of Computer Science at
Stanford University. His research interests include probabilistic deep
learning, uncertainty quantification, experimental design, and ML for
science.