论文标题
对结构化预测的Pac-Bayesian观点，具有隐式损失嵌入
A PAC-Bayesian Perspective on Structured Prediction with Implicit Loss Embeddings
论文作者
论文摘要
许多实用的机器学习任务可以被构建为结构化的预测问题，其中几个输出变量被预测并被视为相互依存。结构化预测的最新理论进步集中在获得快速汇总保证的保证，尤其是在隐式损失嵌入（ILE）框架中。 Pac-Bayes最近因其为预测分布产生严重的风险范围的能力而引起了兴趣。这项工作提出了对ILE结构化预测框架的新型Pac-Bayes观点。我们提出了两个概括性范围，即风险和多余的风险，这些范围对ILE预测变量的行为产生了见解。两种学习算法来自这些界限。实现了算法并分析了其行为，并在\ url {https://github.com/theophilec/paac-bayes-ile-sonstructred-prediction}提供源代码。
Many practical machine learning tasks can be framed as Structured prediction problems, where several output variables are predicted and considered interdependent. Recent theoretical advances in structured prediction have focused on obtaining fast rates convergence guarantees, especially in the Implicit Loss Embedding (ILE) framework. PAC-Bayes has gained interest recently for its capacity of producing tight risk bounds for predictor distributions. This work proposes a novel PAC-Bayes perspective on the ILE Structured prediction framework. We present two generalization bounds, on the risk and excess risk, which yield insights into the behavior of ILE predictors. Two learning algorithms are derived from these bounds. The algorithms are implemented and their behavior analyzed, with source code available at \url{https://github.com/theophilec/PAC-Bayes-ILE-Structured-Prediction}.
