Invariant Theory for Maximum Likelihood Estimation
Offered By: Fields Institute via YouTube
Course Description
Overview
Explore the connections between maximum likelihood estimation and invariant theory in this 38-minute lecture by Anna Seigal from the University of Oxford. Delve into log-linear models and Gaussian group models as part of the Workshop on Real Algebraic Geometry and Algorithms for Geometric Constraint Systems. Learn how optimization problems in statistical models relate to stability concepts in invariant theory. Discover the research findings from Seigal's collaborative work with Carlos Améndola, Kathlén Kohn, and Philipp Reichenbach. Follow the lecture's progression through topics such as groups and statistics, MLE correspondence, and Gaussian group models, culminating in a comprehensive proof.
Syllabus
Introduction
Groups and Statistics
Maximum Likelihood Estimation
MLE
Correspondence
Gaussian Group Models
Proof
Taught by
Fields Institute
Related Courses
Invariant Theory for Computer ScientistsSimons Institute via YouTube A Recent Perspective on Invariant Theory - Viswambhara Makam
Institute for Advanced Study via YouTube Operator Scaling via Geodesically Convex Optimization, Invariant Theory and Polynomial Identity Testing - Yuanzhi Li
Institute for Advanced Study via YouTube Ideals and Varieties of the Pinhole Camera
Joint Mathematics Meetings via YouTube Proving Algebraic Identities
Joint Mathematics Meetings via YouTube