# Transfer Learning for Quantum Classifiers: An Information-Theoretic Generalization Analysis

arXiv: https://arxiv.org/abs/2201.06297 · HTML: https://mlsanity.com/paper/2201.06297/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 17 Jan 2022.

## Builds on (most cited first, 8 of 8)

- [The power of quantum neural networks](https://mlsanity.com/paper/2011.00027/) (2020)
- [Generalization in quantum machine learning from few training data](https://mlsanity.com/paper/2111.05292/) (2021)
- [On the Theory of Transfer Learning: The Importance of Task Diversity](https://mlsanity.com/paper/2006.11650/) (2020)
- [Transfer learning in hybrid classical-quantum neural networks](https://mlsanity.com/paper/1912.08278/) (2019)
- [Encoding-dependent generalization bounds for parametrized quantum circuits](https://mlsanity.com/paper/2106.03880/) (2021)
- [Stochastic gradient descent for hybrid quantum-classical optimization](https://mlsanity.com/paper/1910.01155/) (2019)
- [Information-theoretic analysis for transfer learning](https://mlsanity.com/paper/2005.08697/) (2020)
- [Information-Theoretic Bounds on Transfer Generalization Gap Based on Jensen-Shannon Divergence](https://mlsanity.com/paper/2010.09484/) (2020)

## Built on by (most cited first, 2 of 2)

- [Statistical Complexity of Quantum Learning](https://mlsanity.com/paper/2309.11617/) (2023)
- [On the Generalization of Adversarially Trained Quantum Classifiers](https://mlsanity.com/paper/2504.17690/) (2025)

## Abstract (arXiv)

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'enyi 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.