We initiate the rigorous study of classification in semimetric spaces, which are point sets with a distance function that is non-negative and symmetric, but need not satisfy the triangle inequality. For metric spaces, the doubling dimension essentially characterizes both the runtime and sample complexity of classification algorithms --- yet we show that this is not the case for semimetrics. Instead, we define the {\em density dimension} and discover that it plays a central role in the statistical and algorithmic feasibility of learning in semimetric spaces. We present nearly optimal sample compression algorithms and use these to obtain generalization guarantees, including fast rates. The latter hold for general sample compression schemes and may be of independent interest.
Exploring the Universality of Hadronic Jet Classification
National Tsing Hua University（国立清华大学）；Konkuk University（建国大学）；University of Washington（华盛顿大学）；Lawrence Berkeley National Laboratory（劳伦斯伯克利国家实验室）；University of California, Berkeley（加州大学伯克利分校）
Parton Shower Monte Carlo（PSMC）程序之间的喷气子结构建模存在显着差异。尽管如此，我们观察到在不同PSMC上训练的机器学习分类器学习几乎相同的函数。这意味着当这些分类器应用于相同的PSMC进行测试时，它们会产生几乎相同的性能。这种分类器的通用性表明，在一个模拟上训练并在另一个模拟（或数据）上测试的机器学习模型可能是最佳的。我们的观察是基于对应用于LHC模拟洛伦兹助推希格斯喷流标记的浅层和深层神经网络的详细研究。
JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example
Department of Information Engineering and Mathematics, University of Siena（信息工程与数学系，锡耶纳大学）；Department of Electrical and Electronic Engineering, University of Cagliari（电气与电子工程系，卡利亚里大学）
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
The Henry and Marilyn Taub Faculty of Computer Science, Technion（以色列理工学院亨利与玛丽莲·陶布计算机科学学院）；Faculty of Mathematics, Technion（以色列理工学院数学学院）；Department of Computer Science, Purdue University（普渡大学计算机科学系）；Faculty of Data and Decision Sciences, Technion（以色列理工学院数据与决策科学学院）；Google Research（谷歌研究院）
