Главная
Study mode:
on
1
Intro
2
A Recommendation System Problem
3
A Biometric Identification Problem
4
Robust Learning and Estimation - Application
5
A Toy Problem befitting this near-lunch Hour
6
Notation
7
Some Solution Strategies
8
An Alternate Viewpoint
9
AM-RR at work
10
Why AM-RR works?
11
The Proof
12
A Generalized AM-RR
13
Non-toy Problems for relaxed introspection
14
We do have some answers
Description:
Explore robust regression techniques in this 47-minute lecture by Purushottam Kar from the International Centre for Theoretical Sciences. Delve into algorithms and optimization strategies, focusing on real-world applications such as recommendation systems and biometric identification. Learn about various solution strategies, including the Alternating Minimization Robust Regression (AM-RR) method, and understand why it works through detailed proofs. Examine generalized versions of AM-RR and their applications to non-toy problems. This talk, part of a discussion meeting on algorithms and optimization, offers insights into recent advances in learning algorithms, convex and nonconvex optimization, combinatorial optimization, and spectral algorithms.

Robust Regression by Purushottam Kar

International Centre for Theoretical Sciences
Add to list
0:00 / 0:00