通过学习学习算法实现更灵活的PAC-Bayesian元学习
More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms
AI总结：
我们引入了一个基于PAC-Bayesian理论的元学习新框架，通过将元学习直接表达为学习未来任务的学习算法，实现了更灵活的任务间知识转移，并在理论和实验上均证明了其能提升预测质量。
摘要：
我们引入了一个使用PAC-Bayesian理论研究元学习方法的新框架。与先前工作相比，其主要优势在于允许在如何实现任务间的知识转移方面具有更大的灵活性。对于先前的方法，这只能通过学习模型上的先验分布来间接实现。相比之下，我们证明的新的泛化界将元学习过程更直接地表达为学习应该用于未来任务的学习算法。我们框架的灵活性使其适合分析广泛的元学习机制，甚至设计新机制。除了理论贡献外，我们还通过实验证明了我们的框架在实际的元学习机制中提高了预测质量。
英文摘要：
We introduce a new framework for studying meta-learning methods using PAC-Bayesian theory. Its main advantage over previous work is that it allows for more flexibility in how the transfer of knowledge between tasks is realized. For previous approaches, this could only happen indirectly, by means of learning prior distributions over models. In contrast, the new generalization bounds that we prove express the process of meta-learning much more directly as learning the learning algorithm that should be used for future tasks. The flexibility of our framework makes it suitable to analyze a wide range of meta-learning mechanisms and even design new mechanisms. Other than our theoretical contributions we also show empirically that our framework improves the prediction quality in practical meta-learning mechanisms.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
