Robust Estimation and Generative Adversarial Nets
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore robust estimation techniques and their connection to generative adversarial networks in this 44-minute lecture by Chao Gao from the University of Chicago. Delve into Huber's Model, multivariate location depth, and multi-task regression depth. Examine the challenges in covariance matrix estimation and the computational aspects of robust statistics. Gain insights into the advantages of Tukey Median and f-Learning, and understand their theoretical foundations. Discover the relationship between robust estimation and JS-GAN, bridging statistical theory with modern machine learning techniques.
Syllabus
Intro
Huber's Model
An Example
Multivariate Location Depth
Multi-task Regression Depth
Covariance Matrix
Summary
Computational Challenges
Advantages of Tukey Median
f-Learning
theoretical foundation
JS-GAN
Taught by
Simons Institute
Related Courses
K-Means and K-Medians Under Dimension ReductionSimons Institute via YouTube Can Non-Convex Optimization Be Robust?
Simons Institute via YouTube Invariance, Causality and Novel Robustness
Simons Institute via YouTube The Importance of Better Models in Stochastic Optimization
Simons Institute via YouTube Weaving Together Machine Learning, Theoretical Physics, and Neuroscience
Fields Institute via YouTube