Perturbations, Optimization, and Statistics - Paperback

Perturbations, Optimization, and Statistics - Paperback

$141.12
Sale price  $141.12 Regular price 
Skip to product information
Perturbations, Optimization, and Statistics - Paperback

Perturbations, Optimization, and Statistics - Paperback

$141.12
Sale price  $141.12 Regular price 

by Tamir Hazan (Editor), George Papandreou (Editor), Daniel Tarlow (Editor)

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.

Author Biography

Tamir Hazan is Assistant Professor at Technion, Israel Institute of Technology.

George Papandreou is a Research Scientist for Google, Inc.

Daniel Tarlow is a Researcher at Microsoft Research Cambridge, UK.
Number of Pages: 412
Dimensions: 0.84 x 10 x 8 IN
Publication Date: December 05, 2023

Intentional design

We make things that work better and last longer. Our products solve real problems with clean design.

Quality first

We obsess over the details and strive to deliver the best products at the best prices, every time.

Customer care

We're always on your side: keeping our loyal customers happy is our top priority and number one goal.

Feature 1

Made with care and unconditionally loved by our customers, this signature bestseller exceeds all expectations.

Feature 2

Made with care and unconditionally loved by our customers, this signature bestseller exceeds all expectations.

At the heart of every product lies a unique story, driven by our passion for quality and innovation. Each item enhances your everyday life and sparks joy.