HAI Weekly Seminar with Art Owen | Stanford HAI
Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs
Navigate
  • About
  • Events
  • AI Glossary
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News

Your browser does not support the video tag.
eventSeminar

HAI Weekly Seminar with Art Owen

Status
Past
Date
Wednesday, September 29, 2021 10:00 AM - 11:00 AM PST/PDT
Location
Virtual
Topics
Design, Human-Computer Interaction
Overview
Watch Event Recording

Variable Importance, Cohort Shapley Value, and Redlining

Overview
Watch Event Recording
Share
Link copied to clipboard!
Event Contact
Kaci Peel
kpeel@stanford.edu

Related Events

Arvind Narayanan | Adapting to the Transformation of Knowledge Work
May 18, 202612:00 PM - 1:00 PM
May
18
2026

The possibility that AI will automate most cognitive labor is worth taking seriously. How should we adapt to this transformation? I start from the perspective, articulated in the essay “AI as normal technology”, that the true bottlenecks lie downstream of capabilities and that AI’s impacts will unfold gradually over decades. If this is true, there are major gaps in our current evidence infrastructure, because it over-emphasizes the capability layer.

Event

Arvind Narayanan | Adapting to the Transformation of Knowledge Work

May 18, 202612:00 PM - 1:00 PM

The possibility that AI will automate most cognitive labor is worth taking seriously. How should we adapt to this transformation? I start from the perspective, articulated in the essay “AI as normal technology”, that the true bottlenecks lie downstream of capabilities and that AI’s impacts will unfold gradually over decades. If this is true, there are major gaps in our current evidence infrastructure, because it over-emphasizes the capability layer.

Inside the 2026 AI Index Report | Stanford HAI
SeminarMay 20, 202612:00 PM - 1:15 PM
May
20
2026

The AI Index, currently in its ninth year, tracks, collates, distills, and visualizes data relating to artificial intelligence.

Seminar

Inside the 2026 AI Index Report | Stanford HAI

May 20, 202612:00 PM - 1:15 PM

The AI Index, currently in its ninth year, tracks, collates, distills, and visualizes data relating to artificial intelligence.

Eyck Freymann | AI and Strategic Stability: A Framework for U.S.–China Technology Competition
SeminarMay 27, 202612:00 PM - 1:15 PM
May
27
2026

Strategic stability exists when neither side thinks it can improve its strategic outcome by striking first.

Seminar

Eyck Freymann | AI and Strategic Stability: A Framework for U.S.–China Technology Competition

May 27, 202612:00 PM - 1:15 PM

Strategic stability exists when neither side thinks it can improve its strategic outcome by striking first.

Review Art's Slideshow Here

In order to explain what a black box algorithm does, Owen says, we can start by studying which variables are important for its decisions. Variable importance is studied by making hypothetical changes to predictor variables. Changing parameters one at a time can produce input combinations that are outliers or very unlikely.  They can be physically impossible, or even logically impossible. It is problematic to base an explanation on outputs corresponding to impossible inputs. Owen introduces the cohort Shapley (CS) measure to avoid this problem, based on Shapley value from cooperative game theory.

There are many tradeoffs in picking a variable importance measure, so CS is not the unique reasonable choice. One interesting property of CS is that it can detect 'redlining', meaning the impact of a protected variable on an algorithm's output when that algorithm was trained without the protected variable.

Art Owen
Professor of Statistics, Stanford University