Please note: In order to keep Hive up to date and provide users with the best features, we are no longer able to fully support Internet Explorer. The site is still available to you, however some sections of the site may appear broken. We would encourage you to move to a more modern browser like Firefox, Edge or Chrome in order to experience the site fully.

Supporting your high street Find out how »
Perturbations, Optimization, and Statistics, Hardback Book

Perturbations, Optimization, and Statistics Hardback

Edited by Tamir (Technion -- Israel Institute of Technology) Hazan, George (Research Scientist, Google, Inc.) Papandreou, Daniel (Researcher, Microsoft Research) Tarlow

Part of the Perturbations, Optimization, and Statistics series

Hardback

Out of stock

Description

A description of perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees. In nearly all machine learning, decisions must be made given current knowledge.

Surprisingly, making what is believed to be the best decision is not always the best strategy, even when learning in a supervised learning setting.

An emerging body of work on learning under different rules applies perturbations to decision and learning procedures.

These methods provide simple and highly efficient learning rules with improved theoretical guarantees.

This book describes perturbation-based methods developed in machine learning to augment novel optimization methods with strong statistical guarantees, offering readers a state-of-the-art overview. Chapters address recent modeling ideas that have arisen within the perturbations framework, including Perturb & MAP, herding, and the use of neural networks to map generic noise to distribution over highly structured data.

They describe new learning procedures for perturbation models, including an improved EM algorithm and a learning algorithm that aims to match moments of model samples to moments of data.

They discuss understanding the relation of perturbation models to their traditional counterparts, with one chapter showing that the perturbations viewpoint can lead to new algorithms in the traditional setting. And they consider perturbation-based regularization in neural networks, offering a more complete understanding of dropout and studying perturbations in the context of deep neural networks.

Information

£7.99

Out of stock
Add to Basket
Sign in to add to wishlist
 
Free Home Delivery

on all orders

 
Pick up orders

from local bookshops

Information