LSTM-QGAN: Scalable NISQ Generative Adversarial Network
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910777373360128 |
|---|---|
| author | Chu, Cheng Hastak, Aishwarya Chen, Fan |
| author_facet | Chu, Cheng Hastak, Aishwarya Chen, Fan |
| contents | Current quantum generative adversarial networks (QGANs) still struggle with practical-sized data. First, many QGANs use principal component analysis (PCA) for dimension reduction, which, as our studies reveal, can diminish the QGAN's effectiveness. Second, methods that segment inputs into smaller patches processed by multiple generators face scalability issues. In this work, we propose LSTM-QGAN, a QGAN architecture that eliminates PCA preprocessing and integrates quantum long short-term memory (QLSTM) to ensure scalable performance. Our experiments show that LSTM-QGAN significantly enhances both performance and scalability over state-of-the-art QGAN models, with visual data improvements, reduced Frechet Inception Distance scores, and reductions of 5x in qubit counts, 5x in single-qubit gates, and 12x in two-qubit gates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_02212 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LSTM-QGAN: Scalable NISQ Generative Adversarial Network Chu, Cheng Hastak, Aishwarya Chen, Fan Quantum Physics Signal Processing Current quantum generative adversarial networks (QGANs) still struggle with practical-sized data. First, many QGANs use principal component analysis (PCA) for dimension reduction, which, as our studies reveal, can diminish the QGAN's effectiveness. Second, methods that segment inputs into smaller patches processed by multiple generators face scalability issues. In this work, we propose LSTM-QGAN, a QGAN architecture that eliminates PCA preprocessing and integrates quantum long short-term memory (QLSTM) to ensure scalable performance. Our experiments show that LSTM-QGAN significantly enhances both performance and scalability over state-of-the-art QGAN models, with visual data improvements, reduced Frechet Inception Distance scores, and reductions of 5x in qubit counts, 5x in single-qubit gates, and 12x in two-qubit gates. |
| title | LSTM-QGAN: Scalable NISQ Generative Adversarial Network |
| topic | Quantum Physics Signal Processing |
| url | https://arxiv.org/abs/2409.02212 |