A key component of a quantum machine learning model operating on classical inputs is the design of an embedding circuit mapping inputs to a quantum state. This paper studies a transfer learning setting in which classical-to-quantum embedding is carried out by an arbitrary parametric quantum circuit that is pre-trained based on data from a source task. At run time, a binary quantum classifier of the embedding is optimized based on data from the target task of interest. The average excess risk, i.e., the optimality gap, of the resulting classifier depends on how (dis)similar the source and target tasks are. We introduce a new measure of (dis)similarity between the binary quantum classification tasks via the trace distances. An upper bound on the optimality gap is derived in terms of the proposed task (dis)similarity measure, two R$é$nyi mutual information terms between classical input and quantum embedding under source and target tasks, as well as a measure of complexity of the combined space of quantum embeddings and classifiers under the source task. The theoretical results are validated on a simple binary classification example.
Best sources forward: domain generalization through source-specific nets
Sapienza University of Rome（罗马第一大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Mapillary Research（Mapillary研究院）；Italian Institute of Technology（意大利技术研究院）；University of Trento（特伦托大学）
Invariant Information Bottleneck for Domain Generalization
Microsoft Research Asia（微软亚洲研究院）；Hong Kong University of Science and Technology（香港科技大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；University of California, Berkeley（加州大学伯克利分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
On the Generalization of Adversarially Trained Quantum Classifiers
Department of Computer Science, University of Birmingham, UK（英国伯明翰大学计算机科学系）；KCLIP Lab Centre for Intelligent Information Processing Systems (CIIPS) Department of Engineering, King’s College London, UK（伦敦国王学院工程系智能信息处理系统中心）
