Loss Minimization Yields Multicalibration for Large Neural Networks

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=WJfIOfAZu9g


Duration: 26:25
431 views
9

Adam Kalai (Microsoft)
https://simons.berkeley.edu/talks/adam-kalai-microsoft-2023-04-25
Multigroup Fairness and the Validity of Statistical Judgment



Other Videos By Simons Institute for the Theory of Computing


2023-04-28Indistinguishable Generative Models of Huge Objects
2023-04-28Complexity-theoretic Implications of Multicalibration: ...
2023-04-27From Pseudorandomness to Multi-Group Fairness and Back
2023-04-27What Statistics Can We Multicalibrate? A Characterization via Property Elicitation
2023-04-27Robust Conditional Average Treatment Effect Estimation via Multi-Accurate Learning
2023-04-27Is Your Model Predicting the Past?
2023-04-27Difficult Lessons on Social Prediction from Wisconsin Public Schools
2023-04-26Unfairness Across the Machine Learning Pipeline
2023-04-26A Unifying Perspective on Multi-Calibration: Unleashing Game Dynamics for Multi-Objective Learning
2023-04-26Algorithms for Multi-Group Learning
2023-04-26Loss Minimization Yields Multicalibration for Large Neural Networks
2023-04-26Measuring Distribution Drift via Multicalibration
2023-04-26Phase Transition in Random Circuit Sampling | Quantum Colloquium
2023-04-26Online Omniprediction
2023-04-26Robust Multivalid Conformal Prediction
2023-04-25Calibration: Unbiased Answers to Arbitrary Questions
2023-04-25Validity of Decision Making Algorithms
2023-04-25Multi-Group Fairness and Loss Minimization
2023-04-25Multicalibration and Outcome Indistinguishability II
2023-04-24Multicalibration and Outcome Indistinguishability I
2023-04-22SAT Beyond Boolean Interpretations


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Multigroup Fairness and the Validity of Statistical Judgment
Adam Kalai