DMCA
DS-GA-1003/CSCI-GA.2567 Problem Set 3 1 Machine Learning and Computational Statistics, Fall 2014
BibTeX
@MISC{_ds-ga-1003/csci-ga.2567problem,
author = {},
title = {DS-GA-1003/CSCI-GA.2567 Problem Set 3 1 Machine Learning and Computational Statistics, Fall 2014},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
problem set policy on the course web site. Instructions. You may use the programming language of your choice. However, you are not permitted to use or reference any machine learning code or packages not written by yourself, except for question 2(d)-(g). Your answers to the below questions, including plots and all code that you write for this assignment, should be e-mailed as a PDF document to Akshay Kumar. 1. In this question, you will implement the Pegasos algorithm [5] to optimize the SVM ob-jective using stochastic sub-gradient descent and revisit the spam data. To be consistent with the paper, this question uses the following form of the SVM objective: λ2 ‖w‖2 + 1 m
