Do Simpler Models Exist and How Can We Find Them? - Cynthia Rudin

Explore the concept of simpler models in machine learning and their potential advantages in this 58-minute lecture by Cynthia Rudin at the Institute for Advanced Study. Delve into topics such as the criminal justice system, complicated models, and the Rashomon Set. Examine simpler abstract settings, experiment results, and the Rashomon Curve. Gain insights into learning theory, decision trees, and their limitations. Investigate the rational ratio, the problem of overfitting, and participate in a Q&A session. Discover how simpler models can be identified and applied in various fields, potentially leading to more interpretable and effective solutions.

Introduction
Criminal Justice System
Complicated Models
The Rashomon Set
Simpler Abstract Setting
Experiment Results
The Rashomon Curve
Learning Theory
Prize
Decision Trees
Problem with Decision Trees
Summary
Questions
Rational Ratio
Sharing a Window
Overfitting