Explore recent advancements in high-dimensional learning through this lecture by MIT's Ankur Moitra at the Simons Institute's Probability, Geometry, and Computation in High Dimensions Boot Camp. Delve into the origins of factor analysis, examining the rotation problem and generics algorithm. Discover applications in phylogenetic reconstruction and hidden Markov models. Investigate solid genetic reconstruction, distance functions, and Chang's Lemma. Analyze conditional independence, path learning, and orbit retrieval. Gain insights into orbit tensor decomposition and explore future directions in this field.
Recent Progress in High-Dimensional Learning
Overview
Syllabus
Introduction
Origins of Factor Analysis
The Experiment
The Rotation Problem
Generics Algorithm
Generics Theorem
Applications
Phylogenetic Reconstruction
Hidden Markov Model
Solid Genetic Reconstruction
Distance Function
Changs Lemma
Conditional Independence
Path Learning
Orbit Retrieval
Orbit Tensor Decomposition
The Blueprint
Whats Next
Taught by
Simons Institute
