Accelerated Optimization for Machine Learning

Accelerated Optimization for Machine Learning
PDF, ePUB
  • eBook:
    Accelerated Optimization for Machine Learning: First-Order Algorithms
  • Author:
    Zhouchen Lin, Huan Li, Cong Fang
  • Edition:
    1st ed. 2020 Edition
  • Categories:
  • Data:
    May 28, 2020
  • ISBN:
    9811529094
  • ISBN-13:
    9789811529092
  • Language:
    English
  • Pages:
    297 pages
  • Format:
    PDF, ePUB

Book Description
This book on optimization includes forewords by Michael I. Jordan, Zongben Xu and Zhi-Quan Luo. Machine learning relies heavily on optimization to solve problems with its learning models, and first-order optimization algorithms are the mainstream approaches. The acceleration of first-order optimization algorithms is crucial for the efficiency of machine learning.
Written by leading experts in the field, this book provides a comprehensive introduction to, and state-of-the-art review of accelerated first-order optimization algorithms for machine learning. It discusses a variety of methods, including deterministic and stochastic algorithms, where the algorithms can be synchronous or asynchronous, for unconstrained and constrained problems, which can be convex or non-convex. Offering a rich blend of ideas, theories and proofs, the book is up-to-date and self-contained. It is an excellent reference resource for users who are seeking faster optimization algorithms, as well as for graduate students and researchers wanting to grasp the frontiers of optimization in machine learning in a short time.

Content

1. Introduction
2. Accelerated Algorithms for Unconstrained Convex Optimization
3. Accelerated Algorithms for Constrained Convex Optimization
4. Accelerated Algorithms for Nonconvex Optimization
5. Accelerated Stochastic Algorithms
6. Accelerated Parallel Algorithms
7. Conclusions

Download Accelerated Optimization for Machine Learning: First-Order Algorithms PDF or ePUB format free


Free sample

Download in .PDF format



Download in .ePUB format


Add comments
Прокомментировать
Введите код с картинки:*
Кликните на изображение чтобы обновить код, если он неразборчив
Copyright © 2019