paper-with-me

Papers

Beyond $\mathcal{H}$-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence

2020-07-30 · Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné, Boyu Wang

We reveal the incoherence between the widely-adopted empirical domain adversarial training and its generally-assumed theoretical counterpart based on $\mathcal{H}$-divergence. Concretely, we find that $\mathcal{H}$-divergence is not equivalent to Jensen-Shannon divergence, the optimization objective in domain adversarial training. To this end, we establish a new theoretical framework by directly proving the upper and lower target risk bounds based on joint distributional Jensen-Shannon divergence. We further derive bi-directional upper bounds for marginal and conditional shifts. Our framework exhibits inherent flexibilities for different transfer learning problems, which is usable for various scenarios where $\mathcal{H}$-divergence-based theory fails to adapt. From an algorithmic perspective, our theory enables a generic guideline unifying principles of semantic conditional matching, feature marginal matching, and label marginal shift correction. We employ algorithms for each principle and empirically validate the benefits of our framework on real datasets.

📄 PDF Abstract BibTeX arXiv:2007.15567

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationTransfer Learning

Similar Papers 제목 키워드 기반

Multi-step domain adaptation by adversarial attack to $\mathcal{H} Δ\mathcal{H}$-divergence

2022-07-18 · Arip Asadulaev, Alexander Panfilov, Andrey Filchenkov

Adversarial examples are transferable between different models. In our paper, we propose to use this property for multi-step domain adaptation. In unsupervised domain adaptation settings, we demonstrate that replacing th…

Adversarial AttackDomain AdaptationUnsupervised Domain Adaptation

Towards the Fundamental Limits of Knowledge Transfer over Finite Domains

2023-10-11 · Qingyue Zhao, Banghua Zhu

We characterize the statistical efficiency of knowledge transfer through $n$ samples from a teacher to a probabilistic student classifier with input space $\mathcal S$ over labels $\mathcal A$. We show that privileged in…

Transfer Learning

f-Domain-Adversarial Learning: Theory and Algorithms for Unsupervised Domain Adaptation with Neural Networks

2021-01-01 · David Acuna, Guojun Zhang, Marc T Law, Sanja Fidler

The problem of unsupervised domain adaptation arises in a variety of practical applications where the distribution of the training samples differs from those used at test time. The existing theory of domain adaptation de…

Domain AdaptationGeneralization BoundsLearning TheoryUnsupervised Domain Adaptation

KL Divergence Estimation with Multi-group Attribution

2022-02-28 · Parikshit Gopalan, Nina Narodytska, Omer Reingold, Vatsal Sharan 외

Estimating the Kullback-Leibler (KL) divergence between two distributions given samples from them is well-studied in machine learning and information theory. Motivated by considerations of multi-group fairness, we seek K…

Fairness

Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation

2020-04-22 · Xi Wu, Yang Guo, Jiefeng Chen, YIngyu Liang 외

We consider representation learning (hypothesis class $\mathcal{H} = \mathcal{F}\circ\mathcal{G}$) where training and test distributions can be different. Recent studies provide hints and failure examples for domain inva…

Domain AdaptationRepresentation Learning