Quantum Long Short-term Memory with Differentiable Architecture Search
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912546184757248 |
|---|---|
| author | Chen, Samuel Yen-Chi Tiwari, Prayag |
| author_facet | Chen, Samuel Yen-Chi Tiwari, Prayag |
| contents | Recent advances in quantum computing and machine learning have given rise to quantum machine learning (QML), with growing interest in learning from sequential data. Quantum recurrent models like QLSTM are promising for time-series prediction, NLP, and reinforcement learning. However, designing effective variational quantum circuits (VQCs) remains challenging and often task-specific. To address this, we propose DiffQAS-QLSTM, an end-to-end differentiable framework that optimizes both VQC parameters and architecture selection during training. Our results show that DiffQAS-QLSTM consistently outperforms handcrafted baselines, achieving lower loss across diverse test settings. This approach opens the door to scalable and adaptive quantum sequence learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14955 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Quantum Long Short-term Memory with Differentiable Architecture Search Chen, Samuel Yen-Chi Tiwari, Prayag Machine Learning Artificial Intelligence Emerging Technologies Neural and Evolutionary Computing Quantum Physics Recent advances in quantum computing and machine learning have given rise to quantum machine learning (QML), with growing interest in learning from sequential data. Quantum recurrent models like QLSTM are promising for time-series prediction, NLP, and reinforcement learning. However, designing effective variational quantum circuits (VQCs) remains challenging and often task-specific. To address this, we propose DiffQAS-QLSTM, an end-to-end differentiable framework that optimizes both VQC parameters and architecture selection during training. Our results show that DiffQAS-QLSTM consistently outperforms handcrafted baselines, achieving lower loss across diverse test settings. This approach opens the door to scalable and adaptive quantum sequence learning. |
| title | Quantum Long Short-term Memory with Differentiable Architecture Search |
| topic | Machine Learning Artificial Intelligence Emerging Technologies Neural and Evolutionary Computing Quantum Physics |
| url | https://arxiv.org/abs/2508.14955 |