An Improvement to the Domain Adaptation Bound in a PAC-Bayesian context
نویسندگان
چکیده
This paper provides a theoretical analysis of domain adaptation based on the PACBayesian theory. We propose an improvement of the previous domain adaptation bound obtained by Germain et al. [1] in two ways. We first give another generalization bound tighter and easier to interpret. Moreover, we provide a new analysis of the constant term appearing in the bound that can be of high interest for developing new algorithmic solutions.
منابع مشابه
PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers PAC-Bayesian Theorems for Multiview Learning
Abstract In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand, we propose an improvement of the previous approach proposed by Germain et al. (2013), that relies on a novel distribution pseudodistance based on a ...
متن کاملPAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
In this paper, we provide two main contributions in PAC-Bayesian theory for domain adaptation where the objective is to learn, from a source distribution, a well-performing majority vote on a different target distribution. On the one hand, we propose an improvement of the previous approach proposed by Germain et al. (2013), that relies on a novel distribution pseudodistance based on a disagreem...
متن کاملA PAC-Bayesian Approach for Domain Adaptation with Specialization to Linear Classifiers
We provide a first PAC-Bayesian analysis for domain adaptation (DA) which arises when the learning and test distributions differ. It relies on a novel distribution pseudodistance based on a disagreement averaging. Using this measure, we derive a PAC-Bayesian DA bound for the stochastic Gibbs classifier. This bound has the advantage of being directly optimizable for any hypothesis space. We spec...
متن کاملA New PAC-Bayesian Perspective on Domain Adaptation
We study the issue of domain adaptation: we want to adapt a model from a source distribution to a target one. We focus on models expressed as a majority vote. Our main contribution is a novel theoretical analysis of the target risk that is formulated as an upper bound expressing a trade-off between only two terms: (i) the voters’ joint errors on the source distribution, and (ii) the voters’ dis...
متن کاملSupplementary Material to A PAC-Bayesian Approach forDomain Adaptation with Specialization to Linear Classifiers
In this document, Section 1 contains some lemmas used in subsequent proofs, Section 2 presents an extended proof of the bound on the domain disagreement disρ(DS , DT ) (Theorem 3 of the main paper), Section 3 introduces other PAC-Bayesian bounds for disρ(DS , DT ) and RPT (Gρ), Section 4 shows equations and implementation details about PBDA (our proposed learning algorithm for PAC-Bayesian DA t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1501.03002 شماره
صفحات -
تاریخ انتشار 2014