Robust Gradient Descent - Agnostically Estimating an Unknown Affine Transformation
Offered By: Simons Institute via YouTube
Course Description
Overview
Explore a groundbreaking polynomial-time algorithm for robustly learning unknown affine transformations in this 51-minute lecture by Santosh Vempala from Georgia Tech. Delve into the world of independent component analysis (ICA) and discover how this algorithm efficiently constructs estimates for affine transformations using corrupted samples from a uniform distribution on a d-dimensional hypercube. Learn about the algorithm's ability to achieve optimal recovery guarantees and its superiority over previous methods based on moments. Understand the key component, Robust Gradient Descent, and its novel geometric certificate for verifying affine transformations. Gain insights into the iterative improvement process and the algorithm's applications in optimization and algorithm design. This talk, part of the Simons Institute's series, presents joint work with He Jia and Pravesh Kothari, offering a deep dive into advanced concepts in robust estimation and machine learning.
Syllabus
Robust Gradient Descent: Agnostically Estimating an Unknown Affine Transformation...
Taught by
Simons Institute
Related Courses
A Market for Scheduling, with Applications to Cloud ComputingHausdorff Center for Mathematics via YouTube A Polynomial-Time Classical Algorithm for Noisy Random Circuit Sampling
Simons Institute via YouTube An Efficient Quantum Algorithm for Lattice Problems Achieving Subexponential Approximation Factor
Simons Institute via YouTube Beating the Integrality Ratio for S-T-Tours in Graphs
Hausdorff Center for Mathematics via YouTube Optimization: Interior Point Methods - Part 2
Simons Institute via YouTube