Learning Theory and Algorithms for Auctioning and Adaptation Problems

<p>A common assumption in machine learning is that training and testing data are i.i.d. realizations of the same distribution. However, this assumption is often violated in practice: the training and test distributions are often somewhat related but different. For example, the training sample...

Full description

Bibliographic Details
Main Author: Munoz Medina, Andres
Language:EN
Published: New York University 2016
Subjects:
Online Access:http://pqdtopen.proquest.com/#viewpdf?dispub=3740907