Department of Statistics and Data Science, Carnegie Mellon University(卡内基梅隆大学统计与数据科学系);Machine Learning Department, Carnegie Mellon University(卡内基梅隆大学机器学习系)
Yotam Hechtlinger, Barnabás Póczos, Larry Wasserman
Most classifiers operate by selecting the maximum of an estimate of the conditional distribution $p(y|x)$ where $x$ stands for the features of the instance to be classified and $y$ denotes its label. This often results in a {\em hubristic bias}: overconfidence in the assignment of a definite label. Usually, the observations are concentrated on a small volume but the classifier provides definite predictions for the entire space. We propose constructing conformal prediction sets which contain a set of labels rather than a single label. These conformal prediction sets contain the true label with probability $1-α$. Our construction is based on $p(x|y)$ rather than $p(y|x)$ which results in a classifier that is very cautious: it outputs the null set --- meaning "I don't know" --- when the object does not resemble the training examples. An important property of our approach is that adversarial attacks are likely to be predicted as the null set or would also include the true label. We demonstrate the performance on the ImageNet ILSVRC dataset and the CelebA and IMDB-Wiki facial datasets using high dimensional features obtained from state of the art convolutional neural networks.
Cautious optimism for deep parameterized quantum circuits
Leiden University(莱顿大学);Fraunhofer Heinrich Hertz Institute(弗劳恩霍夫海因里希·赫兹研究所);Department of Physics and Astronomy(物理与天文学系);University of Waterloo(滑铁卢大学);Vector Institute(向量研究所);Porsche Digital GmbH(保时捷数字有限公司)
Equivariant Evidential Deep Learning for Interatomic Potentials
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);College of Computer Science and Artificial Intelligence, Fudan University(复旦大学计算机科学与人工智能学院);The Chinese University of Hong Kong(香港中文大学);Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning
University of British Columbia(不列颠哥伦比亚大学);University of California San Diego(加利福尼亚大学圣迭戈分校);Sony Computer Science Laboratories Inc.(索尼计算机科学实验室公司);RIKEN Center for Advanced Intelligence Project(理化学研究所高级智能中心);CIFAR AI Chair(加拿大高级研究所人工智能讲席);Alberta Machine Intelligence Institute(阿尔伯塔省机器智能研究所)