Georgetown University(乔治城大学);Boston University(波士顿大学);IBM Research – Almaden(IBM阿尔马登研究中心);Weizmann Institute of Science(魏茨曼科学研究所);Northeastern University(东北大学)
Kobbi Nissim, Adam Smith, Thomas Steinke, Uri Stemmer, Jonathan Ullman
While statistics and machine learning offer numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset. A recent line of work has introduced powerful, general purpose algorithms that ensure post hoc generalization (also called robust or post-selection generalization), which says that, given the output of the algorithm, it is hard to find any statistic for which the data differs significantly from the population it came from.
In this work we show several limitations on the power of algorithms satisfying post hoc generalization. First, we show a tight lower bound on the error of any algorithm that satisfies post hoc generalization and answers adaptively chosen statistical queries, showing a strong barrier to progress in post selection data analysis. Second, we show that post hoc generalization is not closed under composition, despite many examples of such algorithms exhibiting strong composition properties.
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection
Korea University(高丽大学)
我们专注于多轮响应选择检索为基础的对话系统。在本文中,我们利用强大的预训练语言模型双向编码器表示从Transformer(BERT)的多轮对话系统,并提出了一个高效的特定领域的语料后训练方法。虽然BERT很容易被各种NLP任务采用,并且优于每个任务的先前基线,但如果任务语料库过于集中于某个领域,它仍然存在局限性。在特定领域语料库上进行后训练(例如,Ubuntu语料库)帮助模型训练不出现在一般语料库中的上下文化表示和单词(例如,English Wikipedia).实验结果表明,我们的方法实现了新的国家的最先进的两个响应选择基准(即,Ubuntu Corpus V1,Advising Corpus)性能提升5.9%,R@1上提升6%。
Machine-learned syndrome post-selection for reliable quantum error correction
Quantum Research Center, Technology Innovation Institute, Abu Dhabi, UAE(量子研究中心、技术创新研究所、阿布扎比、阿联酋);Campus Arapiraca, Federal University of Alagoas, Arapiraca-AL, Brazil(阿拉戈斯联邦大学阿帕里卡校区、巴西)
Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution
Tsinghua University(清华大学);Microsoft Research Asia(微软亚洲研究院);National Engineering Research Center for Software Engineering, Peking University(北京大学软件工程国家工程研究中心)
Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection
School of Statistics and Data Science, KLMDASR, LEBPS, and LPMC, Nankai University(统计与数据科学学院,KLMDASR,LEBPS和LPMC,南开大学);Image Processing Center, School of Astronautics, Beihang University(图像处理中心,航空学院,北航);School of Computer Science and Technology, Tiangong University(计算机科学与技术学院,天工大学)