Gradient-Based Algorithms for Zeroth-Order Optimization

Prashanth L. A., Shalabh Bhatnagar

$161.95 $129.89

Paperback

Not in-store but you can order this
How long will it take?

Availability Information

We source books from suppliers in Australia and overseas. For books we don't currently have in stock, the time it takes to get them from our suppliers can vary widely - from a few days to a few months - so we check each book with each supplier to determine the expected time it will take to be supplied to us.

We then advise you accordingly. If the time taken to get any book is too long for you, you can let us know and we will cancel or adjust your order, and refund as required.

To find out the anticipated arrival time for specific items prior to ordering, please contact us by phone or email:

Phone +61 2 9264 3111, or 1800 4 BOOKS (1800 4 26657) if outside Sydney:
option 1 Abbey's Bookshop (Crime, History, Science, Kids & more) • info@abbeys.com.au
option 2 Language Book Centre (ESL & Foreign Languages) • language@abbeys.com.au
option 3 Galaxy Bookshop (Sci-fi, Fantasy, Romance, Graphic Novels) • sf@galaxybooks.com.au

QTY:

English

now publishers Inc
14 May 2025

Computer security

Series: Foundations and Trends® in Artificial Intelligence

This monograph deals with methods for stochastic or data-driven optimization. The overall goal of these methods is to minimize a certain parameter-dependent objective function that for any parameter value is an expectation of a noisy sample performance objective whose measurement can be made from a real system or a simulation device depending on the setting used. A class of model-free approaches based on stochastic approximation is presented which involve random search procedures to efficiently make use of the noisy observations. The idea here is to simply estimate the minima of the expected objective via an incremental-update or recursive procedure and not to estimate the whole objective function itself. Both asymptotic as well as finite sample analyses of the procedures used for convex as well as non-convex objectives are presented.

The monograph also includes algorithms that either estimate the gradient in gradient-based schemes or estimate both the gradient and the Hessian in Newton-type procedures using random direction approaches involving noisy function measurements. Hence the class of approaches studied fall under the broad category of zeroth order optimization methods. Both asymptotic convergence guarantees in the general setup as well as asymptotic normality results for various algorithms are presented, and also provided is an introduction to stochastic recursive inclusions and their asymptotic convergence analysis. This is necessitated because many of these settings involve set-valued maps for any given parameter. Finally, several interesting applications of these methods in the domain of reinforcement learning are included, and the appendices at the end quickly summarize the basic material for this text.

By: Prashanth L. A., Shalabh Bhatnagar
Imprint: now publishers Inc
Country of Publication: United States
Dimensions: Height: 182mm, Width: 156mm,
Weight: 495g
ISBN: 9781638285441
ISBN 10: 1638285446
Series: Foundations and Trends® in Artificial Intelligence
Pages: 348
Publication Date: 14 May 2025
Audience: Professional and scholarly , Undergraduate
Format: Paperback
Publisher's Status: Active

Preface 1. Introduction 2. Stochastic Approximation 3. Gradient Estimation 4. Asymptotic Analysis of Stochastic Gradient Algorithms 5. Non-Asymptotic Analysis of Stochastic Gradient Algorithms 6. Hessian Estimation and a Stochastic Newton Algorithm 7. Escaping Saddle Points 8. Applications to Reinforcement Learning Appendices Index References

LOW FLAT RATE $9.90 AUST-WIDE DELIVERY

Gradient-Based Algorithms for Zeroth-Order Optimization

Prashanth L. A., Shalabh Bhatnagar

$161.95 $129.89

Paperback

See Also

Contact Abbeys

Contact Galaxy

Contact Language

Contact Us

About ABBEY'S