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

arXiv: https://arxiv.org/abs/1503.06944 · HTML: https://mlsanity.com/paper/1503.06944/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2015.

## Built on by (most cited first, 4 of 4)

- [PAC-Bayesian Domain Adaptation Bounds for Multi-view learning](https://mlsanity.com/paper/2401.01048/) (2024)
- [On the inductive biases of deep domain adaptation](https://mlsanity.com/paper/2109.07920/) (2021)
- [Multi-View Majority Vote Learning Algorithms: Direct Minimization of PAC-Bayesian Bounds](https://mlsanity.com/paper/2411.06276/) (2024)
- [Domain Adaptive Semantic Segmentation by Optimal Transport](https://mlsanity.com/paper/2303.16435/) (2023)

## Abstract (arXiv)

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 disagreement averaging, allowing us to derive a new tighter PAC-Bayesian domain adaptation bound for the stochastic Gibbs classifier. We specialize it to linear classifiers, and design a learning algorithm which shows interesting results on a synthetic problem and on a popular sentiment annotation task. On the other hand, we generalize these results to multisource domain adaptation allowing us to take into account different source domains. This study opens the door to tackle domain adaptation tasks by making use of all the PAC-Bayesian tools.