Using Theories of Decision-Making Under Uncertainty to Improve Data Visualization

Published on ● Video Link: https://www.youtube.com/watch?v=IhGydZwUKc8



Duration: 59:46
2,305 views
31


Jessica Hullman (Northwestern University)
https://simons.berkeley.edu/events/law-society-fellow-talk
Law & Society Fellow Talk

Abstract: Research and development in computer science and statistics have produced increasingly sophisticated software interfaces for interactive visual data analysis as well as data communication. However, our understanding of how to design robust visualizations for data-driven inference remains limited by researchers' heavy reliance on small user studies and hunches about the role of visual representations in inference. Using examples from recent visualization research, this talk will motivate the need for better-defined objectives and theoretical approaches for measuring the value of a visualization for supporting exploratory data analysis or communication. This talk will discuss recent work in progress at the intersection of visualization and theory.

Bio: Jessica Hullman is the Ginni Rometty Associate Professor of Computer Science at Northwestern University. Her research addresses challenges that arise when people draw inductive inferences from data summaries. Hullman's work has contributed visualization techniques, applications, and evaluative frameworks for improving data-driven inference in applications like visual data analysis, data communication, privacy budget setting, and responsive design. Her current interests include how theorizing reasoning under uncertainty as mediated by representations of data could transform research and practice by providing insight into the value of a better interface. Hullman's work has received best paper awards at top visualization and HCI venues, and she has received a Microsoft Research Faculty Fellowship and NSF CAREER, Medium, and Small awards as PI, among others.

==========================================

Established in 2020, the Simons Institute's Law and Society Fellowships enhance Institute programs that address technologies with profound impacts on human society and with implications for ethics, law, and policy, by supporting a researcher within each who is focused on addressing the broader societal implications of the techniques and technologies addressed within these programs.

Law and Society Fellows participate in the Institute's programs and engage with visiting scientists. Additional contributions include an initial talk on the fellow’s work for visiting researchers at the Simons Institute; and a white paper on recommendations and findings.




Other Videos By Simons Institute for the Theory of Computing


2022-11-30Learning from Viral Content
2022-11-30A Polynomial-Time Classical Algorithm for Noisy Random Circuit Sampling
2022-11-28Sequential Decision Making Problems in Multi-Agent Environments
2022-11-22Highlights from Current Programs part 2:
2022-11-22Unique Challenges and Opportunities in Working with Residential Real Estate Data
2022-11-22Generating Adversarial Examples & Defense Methods For Online Fraud Detection
2022-11-22CrystalBox: Efficient Model-Agnostic Explanations for Deep RL Controllers
2022-11-22Computational Mobility: Learning, Prediction, and Algorithms
2022-11-22zkSaaS: Zero-Knowledge SNARKs as a Service
2022-11-22Introduction and Research Fellows Lightning Talks
2022-11-16Using Theories of Decision-Making Under Uncertainty to Improve Data Visualization
2022-11-15Graphons and Graphexes as Models of Large Sparse Networks
2022-11-11Re-designing Recommendation on VolunteerMatch: Theory and Practice
2022-11-11Efficient and Targeted COVID-19 Border Testing via Reinforcement Learning
2022-11-10Unpacking the Black Box: Regulating Algorithmic Decisions
2022-11-10Decision-Aware Learning for Global Health Supply Chains
2022-11-10Supply-Side Equilibria in Recommender Systems
2022-11-10What Really Matters for Fairness in Machine Learning: Delayed Impact and Other Desiderata
2022-11-10Predictive Modeling in Healthcare – Special Considerations
2022-11-10Bringing Order to Chaos: Navigating the Disagreement Problem in Explainable ML
2022-11-09Pipeline Interventions



Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Law & Society Fellow Talk
Jessica Hullman