Bayesian Optimization: Theory and Practice Using Python

ISBN-13: 9781484290620 / Angielski / Miękka / 2023

Peng Liu

Opis

This book covers the essential theory and implementation of popular Bayesian optimization techniques in an intuitive and well-illustrated manner. The techniques covered in this book will enable you to better tune the hyperparemeters of your machine learning models and learn sample-efficient approaches to global optimization.The book begins by introducing different Bayesian Optimization (BO) techniques, covering both commonly used tools and advanced topics. It follows a “develop from scratch” method using Python, and gradually builds up to more advanced libraries such as BoTorch, an open-source project introduced by Facebook recently. Along the way, you’ll see practical implementations of this important discipline along with thorough coverage and straightforward explanations of essential theories. This book intends to bridge the gap between researchers and practitioners, providing both with a comprehensive, easy-to-digest, and useful reference guide. After completing this book, you will have a firm grasp of Bayesian optimization techniques, which you’ll be able to put into practice in your own machine learning models.

What You Will Learn

• Apply Bayesian Optimization to build better machine learning models
• Understand and research existing and new Bayesian Optimization techniques
• Leverage high-performance libraries such as BoTorch, which offer you the ability to dig into and edit the inner working
• Dig into the inner workings of common optimization algorithms used to guide the search process in Bayesian optimization
  

Who This Book Is For

Beginner to intermediate level professionals in machine learning, analytics or other roles relevant in data science.

Spis treści

● Chapter 1: Bayesian Optimization in a Nutshell

o Chapter goal: introducing Bayesian Optimization  workflow and key concepts

o Estimate number of pages: 30

o Sub topics:

▪ What and why of Bayesian Optimization 

▪ Key components in Bayesian Optimization  process

▪ Common Bayesian Optimization  applications

● Chapter 2: Bayesian Optimization in Hyperparameter Tuning

o Chapter goal: Showcase using Bayesian Optimization  for hyperparameter tuning in training better ML models

o Estimate number of pages: 35

o Sub topics:

▪ ML workflow

▪ Common hyperparameter tuning techniques

▪ Advantage of Bayesian Optimization  in tuning hyperparameters for ML models through practical examples

● Chapter 3 : Gaussian Process

o Chapter goal: Introduce Gaussian process and its role in Bayesian Optimization  workflow

o Estimate number of pages: 30

o Sub topics:

▪ Gaussian process  breakdown

▪ Theory illustration on Gaussian process 

▪ Coding Gaussian process  as surrogate model in Bayesian Optimization 

● Chapter 4 : Common Acquisition Function

o Chapter goal: Introduce popular acquisition functions including EI, PI and others

o Estimate number of pages: 35

o Sub topics:

▪ The role of acquisition function in Bayesian Optimization 

▪ Theoretical basics for each common AF

▪ Coding examples

● Chapter 5:  Advanced Acquisition Function

o Chapter goal: Introduce advanced acquisition functions including KG and PE and parallel variants

o Estimate number of pages: 35

o Sub topics:

▪ Theoretical basics for advanced AF

▪ Coding examples

● Chapter 6 : Introducing BoTorch

o Chapter goal: Introduce the recent GPU based package for running Bayesian Optimization  

o Estimate number of pages: 40

o Sub topics:

▪ Introduction of the package and key components

▪ Starting examples

▪ Advanced examples

● Chapter 7 : Case study

o Chapter goal: Demonstrate full working examples using Bayesian Optimization  and BoTorch

o Estimate number of pages: 30

o Sub topics:

▪ Two full coding examples TBD

● Chapter 8 : Exotic Bayesian Optimization Problems

o Chapter goal: Introduce additional Bayesian Optimization  variants such as adding constraints and getting noisy observations

o Estimate number of pages: 30

o Sub topics:

▪ Constrained Bayesian Optimization 

▪ Parallel Bayesian Optimization 

▪ BO with noisy observations

▪ Look ahead Bayesian Optimization 

O autorze

Peng Liu is an assistant professor of quantitative finance (practice) at Singapore Management University and an adjunct researcher at the National University of Singapore.  He holds a Ph.D. in statistics from the National University of Singapore and has ten years of working experience as a data scientist across the banking, technology, and hospitality industries

Blurb

This book covers the essential theory and implementation of popular Bayesian optimization techniques in an intuitive and well-illustrated manner. The techniques covered in this book will enable you to better tune the hyperparemeters of your machine learning models and learn sample-efficient approaches to global optimization.

The book begins by introducing different Bayesian Optimization (BO) techniques, covering both commonly used tools and advanced topics. It follows a “develop from scratch” method using Python, and gradually builds up to more advanced libraries such as BoTorch, an open-source project introduced by Facebook recently. Along the way, you’ll see practical implementations of this important discipline along with thorough coverage and straightforward explanations of essential theories. This book intends to bridge the gap between researchers and practitioners, providing both with a comprehensive, easy-to-digest, and useful reference guide.

After completing this book, you will have a firm grasp of Bayesian optimization techniques, which you’ll be able to put into practice in your own machine learning models.

You will:

• Apply Bayesian Optimization to build better machine learning models
• Understand and research existing and new Bayesian Optimization techniques
• Leverage high-performance libraries such as BoTorch, which offer you the ability to dig into and edit the inner working
• Dig into the inner workings of common optimization algorithms used to guide the search process in Bayesian optimization