Data Science Seminar
Some Very Basic Theory of Classification (in low dimensions
Jeff Phillips
Some Very Basic Theory of Classification (in low dimensions
| When | Friday, February 18, 2022, 3:00 PM – 4:00 PM (MT) |
|---|---|
| Where | WEB 1250 |
Abstract
I plan to talk about some new results on some very fundamental (but overlooked) theory questions in classification. First, how fast can you find a linear classifier that eps-approximates the optimal one in terms of miss-classification? Second, if you want to preserve a Euclidean margin between perfectly classified points for a polynomial classifier, how many samples do you need?
Speaker
Tags: machine learning
Part of the Data Science Seminar. Something wrong on this page? Edit _data/talks/2022-02-18-jeff-phillips.toml.