arXiv (Cornell University) · 2019 · 229 citations · 29 references
ComputingComputer ScienceAlgorithmsMachine LearningOptimizationLoss FunctionOptimization For Machine LearningUnsupervised LearningAdversarial Domain AdaptationDistribution ComparisonDomain AdaptationMargin DiscrepancyMargin-based LossMinimax OptimizationOptimization AlgorithmsScoring Functions
This paper addresses the problem of unsupervised domain adaption from theoretical and algorithmic perspectives. Existing domain adaptation theories naturally imply minimax optimization algorithms, which connect well with the domain adaptation methods based on adversarial learning. However, several disconnections still exist and form the gap between theory and algorithm. We extend previous theories (Mansour et al., 2009c; Ben-David et al., 2010) to multiclass classification in domain adaptation, where classifiers based on the scoring functions and margin loss are standard choices in algorithm design. We introduce Margin Disparity Discrepancy, a novel measurement with rigorous generalization bounds, tailored to the distribution comparison with the asymmetric margin loss, and to the minimax optimization for easier training. Our theory can be seamlessly transformed into an adversarial learning algorithm for domain adaptation, successfully bridging the gap between theory and algorithm. A series of empirical studies show that our algorithm achieves the state of the art accuracies on challenging domain adaptation tasks.
29
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Sinno Jialin Pan, Qiang Yang · IEEE Transactions on Knowledge and Data Engineering · 2009 · 23.2K citations
Adversarial Discriminative Domain Adaptation
Eric Tzeng, Judy Hoffman, Kate Saenko et al. · 2017 · 5K citations
A theory of learning from different domains
Shai Ben-David, John Blitzer, Koby Crammer et al. · Machine Learning · 2009 · 3.5K citations · Full text