.png){kind=icon}
返回
Binary classification with classical instances and quantum labels
.png){kind=icon}
OA
AI
DOI：10.1007/s42484-021-00043-z.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In classical statistical learning theory, one of the most well-studied problems is that of binary classification. The information-theoretic sample complexity of this task is tightly characterized by the Vapnik-Chervonenkis (VC) dimension. A quantum analog of this task, with training data given as a quantum state has also been intensely studied and is now known to have the same sample complexity as its classical counterpart. We propose a novel quantum version of the classical binary classification task by considering maps with classical input and quantum output and corresponding classical-quantum training data. We discuss learning strategies for the agnostic and for the realizable case and study their performance to obtain sample complexity upper bounds. Moreover, we provide sample complexity lower bounds which show that our upper bounds are essentially tight for pure output states. In particular, we see that the sample complexity is the same as in the classical binary classification task w.r.t. its dependence on accuracy, confidence and the VC-dimension.
Keyword:
Quantum learning theory
Sample complexity
Binary classification
VC-dimension
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
Q
IF:
4.4
论文数:
441
被引数:
796
机构
引用论文
Coupling Advanced Modeling and Visualization to Improve High-Impact Tropical Weather Prediction
PREAI
分享收藏分享收藏NO1, a New Sigma 2 Receptor/TMEM97 Fluorescent Ligand, Downregulates SOCE and Promotes Apoptosis in the Triple Negative Breast Cancer Cell Lines.png)
CancersOAAI
CancersIF0
OAAI分享收藏Clinical trial of treatment programs for purulent vaginal discharge in lactating dairy cattle in New Zealand新西兰泌乳奶牛化脓性阴道分泌物治疗方案的临床试验
PREAI
分享收藏Prospective study of cenobamate on cognition, affectivity, and quality of life in focal epilepsy
OAAI
OAAI分享收藏
查看更多内容