Domain Adaptation Theory - 1st Edition - ISBN: 9781785482366

Domain Adaptation Theory

1st Edition

Available Theoretical Results

Authors: Redko Ievgen Emilie Morvant Amaury Habrard Marc Sebban Younès Bennani
Hardcover ISBN: 9781785482366
Imprint: ISTE Press - Elsevier
Published Date: 1st November 2018
Page Count: 250
Sales tax will be calculated at check-out Price includes VAT/GST

Institutional Access

Secure Checkout

Personal information is secured with SSL technology.

Free Shipping

Free global shipping
No minimum order.

Description

Domain Adaptation Theory: Available Theoretical Results gives the current state-of-the-art results on transfer learning, with a particular focus on domain adaptation from a theoretical point-of-view. The book begins with a brief overview of the most popular concepts used to provide generalization guarantees, and includes sections on Vapnik-Chervonenkis (VC), Rademacher, PAC-Bayesian, Robustness and Stability based bounds. In addition, the book explains the domain adaptation problem and describes the four major families of theoretical results that exist in the literature, including the Divergence based bounds. Next, PAC-Bayesian bounds are discussed, including the original PAC-Bayesian bounds for domain adaptation and their updated version.

This part of the book is followed by two sections presenting generalization guarantees based on the robustness and stability properties of the learning algorithm.

Key Features

  • Gives an overview of current results on transfer learning
  • Focuses on the adaptation of the field from a theoretical point-of-view
  • Describes four major families of theoretical results in the literature
  • Summarizes the main existing results in the field of adaptation of the field
  • Provides tips for future research

Readership

Scientists, researchers and engineers interested in this subject area

Table of Contents

  1. Introduction.
    2. State-of-the-art on statistical learning theory.
    3. Domain adaptation problem.
    4. Divergence based bounds.
    5. PAC-Bayes bounds for domain adaptation.
    6. Robustness and adaptation.
    7. Stability and hypothesis transfer learning.
    8. Impossibility results.
    9. Conclusions and open discussions.

Details

No. of pages:
250
Copyright:
© ISTE Press - Elsevier 2019
Published:
Imprint:
ISTE Press - Elsevier
Hardcover ISBN:
9781785482366

About the Author

Redko Ievgen

Ievgen Redko is an associate professor at INSA in Lyon since 2016. He obtained his PhD in computer Science, specialized in Data Science in 2015.

Affiliations and Expertise

Associate Professor, INSA Lyon, University of Lyon

Emilie Morvant

Emilie Morvant is a Lecturer and a professor assistant at the Jean Monnet of Saint-Etienne University. She obtained her PhD in 2013 in Computer Science.

Affiliations and Expertise

Associate Professor, University of Lyon, UJM-Saint-Etienne, CNRS

Amaury Habrard

Amaury Habrard is a full professor at the Jean Monnet of Saint-Etienne University (UJM), he is also a member of the CNRS and the Computer Science department of UJM. He obtained his PhD in 2004 at the University of Saint-Etienne and his habilitation thesis in 2010.

Affiliations and Expertise

Professor, University of Lyon, UJM-Saint-Etienne, CNRS

Marc Sebban

Marc Sebban is a professor at the University of Jean Monnet of Saint-Etienne since 2001. He obtained his accreditation to lead research in 2001 and his PhD in 1996.

Affiliations and Expertise

Professor, University of Lyon, UJM-Saint-Etienne, CNRS

Younès Bennani

Younès Bennani obtained his PhD in 1992, and his accreditation to lead research in 1998. Dr. Younès Bennani joined the Computer Science Laboratory of Paris-Nord (LIPN-CNRS) at Paris 13 University in 1993.

Affiliations and Expertise

Professor, Computer Sceince Laboratory, Paris-Nord, CNRS

Ratings and Reviews