论文标题
使用多数预测器准确性的深度传输学习的概括范围
Generalization Bounds for Deep Transfer Learning Using Majority Predictor Accuracy
论文作者
论文摘要
我们分析了通过从源到目标任务转移学习训练的深度学习模型的新概括范围。我们的边界利用一个称为多数预测器准确性的数量，可以从数据中有效地计算出来。我们表明我们的理论在实践中很有用，因为它意味着大多数预测指标的准确性可以用作可传递性措施，这一事实也通过我们的实验验证。
We analyze new generalization bounds for deep learning models trained by transfer learning from a source to a target task. Our bounds utilize a quantity called the majority predictor accuracy, which can be computed efficiently from data. We show that our theory is useful in practice since it implies that the majority predictor accuracy can be used as a transferability measure, a fact that is also validated by our experiments.
