TY - GEN

T1 - Transfer Learning for Quantum Classifiers

T2 - 2023 IEEE Information Theory Workshop, ITW 2023

AU - Theresa Jose, Sharu

AU - Simeone, Osvaldo

N1 - Publisher Copyright:
© 2023 IEEE.

PY - 2023

Y1 - 2023

N2 - 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 Rényi 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.

AB - 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 Rényi 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.

UR - http://www.scopus.com/inward/record.url?scp=85165099150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85165099150&partnerID=8YFLogxK

U2 - 10.1109/ITW55543.2023.10160236

DO - 10.1109/ITW55543.2023.10160236

M3 - Conference contribution

AN - SCOPUS:85165099150

T3 - 2023 IEEE Information Theory Workshop, ITW 2023

SP - 532

EP - 537

BT - 2023 IEEE Information Theory Workshop, ITW 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 23 April 2023 through 28 April 2023

ER -