AI-Fun Seminar | Gavin Brown: Bias/Variance is not the same as Approximation/Estimation
| Dates: | 27 March 2024 |
|---|
| Times: | 10:30 - 11:30 |
|---|
| What is it: | Seminar |
|---|
| Organiser: | Faculty of Science and Engineering |
|---|
| Who is it for: | University staff, External researchers, Current University students |
|---|
| Speaker: | Gavin Brown |
|---|
|
The Manchester Centre for AI Fundamentals is hosting a series of seminars featuring expert researchers working in the fundamentals of AI and our speaker on 27 March is Professor Gavin Brown.
Title:
Bias/Variance is not the same as Approximation/Estimation
Abstract:
We study the relation between two classical results: the bias-variance decomposition, and the approximation-estimation decomposition. Both are important conceptual tools in Machine Learning, helping us describe the nature of model fitting. It is commonly stated that they are “closely related”, or “similar in spirit”. However, sometimes it is said they are equivalent. In fact, they are different but have subtle connections cutting across learning theory, classical statistics, and information geometry, that (very surprisingly) have not been previously observed. We present several results for losses expressible as Bregman divergences: a broad family with a known bias-variance decomposition. Discussion and future directions are presented for more general losses, including the 0/1 classification loss.
Gavin Brown is Professor of Machine Learning at Manchester. Find him at: profgavinbrown.github.io
Speaker
Gavin Brown
Role: Professor of Computer Science, Machine Learning and Robotics
Organisation: The University of Manchester
Travel and Contact Information
Find event
6.207
University Place
Manchester
