List Decodable Mean Estimation in Nearly Linear Time
Offered By: IEEE via YouTube
Course Description
Overview
Explore a 20-minute IEEE conference talk on List Decodable Mean Estimation, presented by researchers from the University of California Berkeley. Delve into the efficient algorithms for this statistical problem, including a 1/2-inefficient algorithm and the main algorithmic theorem. Learn about finding affine subspaces, generalized packing/covering solvers, and the application of Multiplicative Weights. Gain insights into the nearly linear time solution and discuss conclusions and open questions in this cutting-edge area of computational statistics.
Syllabus
List Decodable Mean Estimation in Nearly Linear Time
List Decodable Mean Estimation: a 1/2
Inefficient Algorithm
Main Algorithmic Theorem: Win-Win
Finding the Affine Subspace
Generalized Packing/Covering Solvers
Multiplicative Weights (PTZ 12)
Conclusions and Open Questions
Taught by
IEEE FOCS: Foundations of Computer Science
Tags
Related Courses
An Improved Exponential-Time Approximation Algorithm for Fully-Alternating Games Against NatureIEEE 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