Advances in Domain Adaptation Theory

Description

Advances in Domain Adaptation Theory gives current, state-of-the-art results on transfer learning, with a particular focus placed 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, including sections on Vapnik-Chervonenkis (VC), Rademacher, PAC-Bayesian, Robustness and Stability based bounds. In addition, the book explains 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. Additional sections present generalization guarantees based on the robustness and stability properties of the learning algorithm. Cover......Page 1 Advances in Domain Adaptation Theory ......Page 3 Copyright_2019 ......Page 4 Abstract ......Page 5 Notations ......Page 7 Introduction ......Page 9 1 State of the Art of Statistical Learning Theory......Page 14 2 Domain Adaptation Problem......Page 33 3 Seminal Divergence-based Generalization Bounds......Page 49 4 Impossibility Theorems for Domain Adaptation......Page 70 5 Generalization Bounds with Integral Probability Metrics......Page 85 6 PAC–Bayesian Theory for Domain Adaptation......Page 103 7 Domain Adaptation Theory Based on Algorithmic Properties......Page 115 8 Iterative Domain Adaptation Methods......Page 131 Conclusions and Discussions......Page 144 Appendix 1. Proofs of the Main Results of Chapter 3......Page 146 Appendix 2. Proofs of the Main Results of Chapter 4......Page 160 Appendix 3. Proofs of the Main Results of Chapter 5......Page 172 Appendix 4. Proofs of the Main Results of Chapter 6......Page 178 Appendix 5. Proofs of the Main Results of Chapter 8......Page 181 References ......Page 184 Index......Page 193