Transferable Equivariant Quantum Circuits for TSP: Generalization Bounds and Empirical Validation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sharma, Monit, Lau, Hoong Chuin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915557816664064
author Sharma, Monit
Lau, Hoong Chuin
author_facet Sharma, Monit
Lau, Hoong Chuin
contents In this work, we address the challenge of generalization in quantum reinforcement learning (QRL) for combinatorial optimization, focusing on the Traveling Salesman Problem (TSP). Training quantum policies on large TSP instances is often infeasible, so existing QRL approaches are limited to small-scale problems. To mitigate this, we employed Equivariant Quantum Circuits (EQCs) that respect the permutation symmetry of the TSP graph. This symmetry-aware ansatz enabled zero-shot transfer of trained parameters from $n-$city training instances to larger m-city problems. Building on recent theory showing that equivariant architectures avoid barren plateaus and generalize well, we derived novel generalization bounds for the transfer setting. Our analysis introduces a term quantifying the structural dissimilarity between $n-$ and $m-$node TSPs, yielding an upper bound on performance loss under transfer. Empirically, we trained EQC-based policies on small $n-$city TSPs and evaluated them on larger instances, finding that they retained strong performance zero-shot and further improved with fine-tuning, consistent with classical observations of positive transfer between scales. These results demonstrate that embedding permutation symmetry into quantum models yields scalable QRL solutions for combinatorial tasks, highlighting the crucial role of equivariance in transferable quantum learning.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14533
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Transferable Equivariant Quantum Circuits for TSP: Generalization Bounds and Empirical Validation
Sharma, Monit
Lau, Hoong Chuin
Quantum Physics
In this work, we address the challenge of generalization in quantum reinforcement learning (QRL) for combinatorial optimization, focusing on the Traveling Salesman Problem (TSP). Training quantum policies on large TSP instances is often infeasible, so existing QRL approaches are limited to small-scale problems. To mitigate this, we employed Equivariant Quantum Circuits (EQCs) that respect the permutation symmetry of the TSP graph. This symmetry-aware ansatz enabled zero-shot transfer of trained parameters from $n-$city training instances to larger m-city problems. Building on recent theory showing that equivariant architectures avoid barren plateaus and generalize well, we derived novel generalization bounds for the transfer setting. Our analysis introduces a term quantifying the structural dissimilarity between $n-$ and $m-$node TSPs, yielding an upper bound on performance loss under transfer. Empirically, we trained EQC-based policies on small $n-$city TSPs and evaluated them on larger instances, finding that they retained strong performance zero-shot and further improved with fine-tuning, consistent with classical observations of positive transfer between scales. These results demonstrate that embedding permutation symmetry into quantum models yields scalable QRL solutions for combinatorial tasks, highlighting the crucial role of equivariance in transferable quantum learning.
title Transferable Equivariant Quantum Circuits for TSP: Generalization Bounds and Empirical Validation
topic Quantum Physics
url https://arxiv.org/abs/2510.14533