EP-IT Data Science Seminars

PHYSTAT seminar: An Overview of Nonparametric Regression

by Prof. Chad Schafer (Carnegie Mellon University)

Europe/Zurich
CERN

CERN

Description

Nonparametric regression lies in the space between simplistic linear models and opaque machine learning tools. Nonparametric models are flexible, allowing the data to dictate the shape of relationships between variables, but are also easier to interpret, and hence allow for greater insight into what may be learned from them, when compared to, e.g., deep learning. This lecture provides an overview of nonparametric regression, focusing on some methods, and a bit of the underlying statistical theory. There will be a discussion of the implications of the curse of dimensionality, and how the additive nonparametric model can be a particularly appealing option to circumvent this "curse." The relationship between additive models and simple neural network architectures is instructive.

The seminar will be done remote only.

Organized by

M. Girone, M. Elsing, L. Moneta, M. Pierini
Event co-organised with the PHYSTAT Committee

Zoom Meeting ID
98545267593
Description
EP/IT Data Science seminar
Host
Lorenzo Moneta
Alternative hosts
Markus Elsing, Maria Girone, Thomas Nik Bazl Fard, Caroline Cazenoves, Pascal Pignereau, EP Seminars and Colloquia, Maurizio Pierini
Passcode
97200142
Useful links
Join via phone
Zoom URL