YoVDO

Smoothed Analysis in Unsupervised Learning via Decoupling

Offered By: IEEE via YouTube

Tags

IEEE FOCS: Foundations of Computer Science Courses Unsupervised Learning Courses Hidden Markov Models Courses High-Dimensional Data Analysis Courses Tensor Decomposition Courses

Course Description

Overview

Explore the concept of smoothed analysis in unsupervised learning through a 21-minute IEEE conference talk. Delve into the smoothed analysis framework, its application to tensor decomposition, and its implications in high-dimensional settings. Learn about the challenges in bounding condition numbers and the intricacies of working with polynomials of perturbed vectors. Discover how this approach applies to robust subspace recovery, Hidden Markov Models, and robust tensor decomposition. Gain insights into the proof of Theorem 1, which underpins the theoretical foundations of this analytical method.

Syllabus

Smoothed Analysis in Unsupervised Learning via Decoupling
Smoothed analysis framework
Smoothed analysis for tensor decomposition
Smoothed analysis in high dimension
Goal Need to bound the condition number
Challenges Within one column of
Polynomials of one perturbed vector
Polynomials of a few perturbed vectors
Robust subspace recovery
Hidden Markov Models
Robust tensor decomposition
Proof of Theorem 1


Taught by

IEEE FOCS: Foundations of Computer Science

Tags

Related Courses

An Improved Exponential-Time Approximation Algorithm for Fully-Alternating Games Against Nature
IEEE via YouTube
Computation in the Brain Tutorial - Part 2
IEEE via YouTube
Computation in the Brain - Part 1
IEEE via YouTube
Spectral Independence in High-Dimensional Expanders and Applications to the Hardcore Model
IEEE via YouTube
Cookbook Lower Bounds for Statistical Inference in Distributed and Constrained Settings - Part 1
IEEE via YouTube