Generative Replay Mitigates Sample Starvation in Quantum Architecture Search
Abstract
Reinforcement learning (RL) can automate quantum architecture search, but its scalability is limited when useful circuit trajectories become rare in the rapidly expanding search space. Existing replay mechanisms reuse observed transitions; the proposed learned model produces additional predicted one step transitions from real state-action seeds. Here we introduce GenQAS, a tensor network-guided RL framework that combines a fixed matrix product state warm-start with prioritized generative replay. A learned local transition model generates synthetic circuit transitions on demand and mixes them with real experience during Double Deep Q-Network updates. Under a random exploration analysis, near ground state circuits occupy a rapidly shrinking region of the accessible state space. We investigate whether real data anchored synthetic replay can improve the effective training signal in this regime. Across chemical Hamiltonian benchmarks from 6 to 12 qubits, GenQAS improves fixed-budget success probability and identifies compact circuits at competitive energy error. At 12 qubits, it improves final success probability by up to 7.0× over passive replay. On a 15-qubit transverse field Ising model, GenQAS increases success probability from 12% to 21%. In a noisy 6-qubit BeH2 transfer experiment, generative replay reduces the steps to chemical accuracy by 92.7%. These results show that generative replay can mitigate sample starvation in quantum architecture search and support more resource efficient circuit discovery.
Related
- Efficient Record-and-Replay Arithmetic for Quantum Elliptic-Curve Point Addition
- Quantum Feature Amplification Network (QFAN) as An Autoregressive Quantum Generative Model
- Generative learning of time series with holographic quantum circuit sampling
- On Certifying Source Sampling Hardness in Quantum Generative Modeling
- Bottom-Up Design of Quantum Optical Experiments Using Discrete Generative Models
BibTeX
@misc{kundu2026generative,
title = {{Generative Replay Mitigates Sample Starvation in Quantum Architecture Search}},
author = {Akash Kundu and Amit Kumar Jaiswal and Sebastian Feld and Prayag Tiwari},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.11248},
eprint = {2609.11248},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.11248},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Generative Replay Mitigates Sample Starvation in Quantum Architecture Search
AU - Akash Kundu
AU - Amit Kumar Jaiswal
AU - Sebastian Feld
AU - Prayag Tiwari
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2609.11248
UR - https://arxiv.org/abs/2609.11248
AB - Reinforcement learning (RL) can automate quantum architecture search, but its scalability is limited when useful circuit trajectories become rare in the rapidly expanding search space. Existing replay mechanisms reuse observed transitions; the proposed learned model produces additional predicted one step transitions from real state-action seeds. Here we introduce GenQAS, a tensor network-guided RL framework that combines a fixed matrix product state warm-start with prioritized generative replay. A learned local transition model generates synthetic circuit transitions on demand and mixes them with real experience during Double Deep Q-Network updates. Under a random exploration analysis, near ground state circuits occupy a rapidly shrinking region of the accessible state space. We investigate whether real data anchored synthetic replay can improve the effective training signal in this regime. Across chemical Hamiltonian benchmarks from 6 to 12 qubits, GenQAS improves fixed-budget success probability and identifies compact circuits at competitive energy error. At 12 qubits, it improves final success probability by up to 7.0× over passive replay. On a 15-qubit transverse field Ising model, GenQAS increases success probability from 12% to 21%. In a noisy 6-qubit BeH_2 transfer experiment, generative replay reduces the steps to chemical accuracy by 92.7%. These results show that generative replay can mitigate sample starvation in quantum architecture search and support more resource efficient circuit discovery.
ER -