## Regularization Paths and Coordinate Descent

author: Trevor Hastie, Stanford University
published: Sept. 26, 2008,   recorded: August 2008,   views: 2364
Categories
You might be experiencing some problems with Your Video player.

# Slides

0:00 Slides - Introduction Fast Regularization Paths via Coordinate Descent Linear Models in Data Mining The elements of statistical learning - the book Linear regression via the Lasso (Tibshirani, 1995) Brief History of `1 Regularization Lasso Coefficient Pro le History of Path Algorithms Lasso Coefficient Pro le History of Path Algorithms Coordinate Descent Graph - LARS and GLMNET Speed Trials Linear Regression | Dense Features Logistic Regression | Dense Features Logistic Regression | Sparse Features Logistic Regression | Real Datasets A brief history of coordinate descent for the lasso (1) A brief history of coordinate descent for the lasso (2) A brief history of coordinate descent for the lasso (3) Coordinate descent for the lasso Why is coordinate descent so fast? Why is coordinate descent so fast? (2) Binary Logistic Models Elastic-net Penalty Leukemia Data, Logistic, N=72, p=3571, rst 10 steps shown Multiclass classi cation Summary Other Applications Undirected Graphical Models Grouped lasso CGH modeling and the fused lasso. Summary

# Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

# Description

In a statistical world faced with an explosion of data, regularization has become an important ingredient. In many problems, we have many more variables than observations, and the lasso penalty and its hybrids have become increasingly useful. This talk presents some effective algorithms based on coordinate descent for fitting large scale regularization paths for a variety of problems. Joint work with Rob Tibshirani and Jerome Friedman