A New PAC-Bayesian Perspective on Domain Adaptation

06/15/2015
by   Pascal Germain, et al.
0

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the trade-off between a source error measure and the target voters' disagreement. Our bound suggests that one has to focus on regions where the source data is informative.From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithmand perform experiments on real data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/17/2017

PAC-Bayes and Domain Adaptation

We provide two main contributions in PAC-Bayesian theory for domain adap...
research
03/24/2015

PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers

In this paper, we provide two main contributions in PAC-Bayesian theory ...
research
12/11/2012

PAC-Bayesian Learning and Domain Adaptation

In machine learning, Domain Adaptation (DA) arises when the distribution...
research
08/30/2022

Super-model ecosystem: A domain-adaptation perspective

This paper attempts to establish the theoretical foundation for the emer...
research
11/19/2013

Domain Adaptation of Majority Votes via Perturbed Variation-based Label Transfer

We tackle the PAC-Bayesian Domain Adaptation (DA) problem. This arrives ...
research
10/01/2014

Domain adaptation of weighted majority votes via perturbed variation-based self-labeling

In machine learning, the domain adaptation problem arrives when the test...
research
08/06/2014

On the Generalization of the C-Bound to Structured Output Ensemble Methods

This paper generalizes an important result from the PAC-Bayesian literat...

Please sign up or login with your details

Forgot password? Click here to reset