skip to main content
Caltech

IST LUNCH BUNCH

Tuesday, March 20, 2018
12:00pm to 1:00pm
Add to Cal
Annenberg 105
CANCELLED Human-Centric Machine Learning: Enabling Machine Learning for High-Stakes Decision-Making
Himabindu Lakkaraju, PhD Student, EECS, Stanford University,

 Domains such as law, healthcare, and public policy often involve highly consequential decisions which are predominantly made by human decision-makers. The growing availability of data pertaining to such decisions offers an unprecedented opportunity to develop machine learning models which can aid human decision-makers in making better decisions. However, the applicability of machine learning to the aforementioned domains is limited by certain fundamental challenges:

    1) The data is selectively labeled i.e., we only observe the outcomes of the decisions made by human decision-makers and not the counterfactuals.


    2) The data is prone to a variety of selection biases and confounding effects.


    3) The successful adoption of the models that we develop depends on how well decision-makers can understand and trust their functionality, however, most of the existing machine learning models are primarily optimized for predictive accuracy and are not very interpretable.

    In this talk, I will describe novel computational frameworks which address the aforementioned challenges, thus, paving the way for large-scale deployment of machine learning models to address problems of significant societal impact. First, I will discuss how to build interpretable predictive models and explanations of complex black box models which can be readily understood and consequently trusted by human decision-makers. I will then outline efficient and provably near-optimal approximation algorithms to solve these problems. Next, I will present a novel evaluation framework which allows us to reliably compare the quality of decisions made by human decision-makers and machine learning models amidst challenges such as missing counterfactuals and presence of unmeasured confounders (unobservables). Lastly, I will provide a brief overview of my research on diagnosing and characterizing biases (systematic errors) in human decisions and predictions of machine learning models.

    I will conclude the talk by sketching future directions which enable effective and efficient collaboration between humans and machine learning models to address problems of societal impact.

For more information, please contact Diane Goodfellow by phone at 6267972398 or by email at [email protected].