Computing the gradients with respect to all parameters of a quantum neural network using a single circuit
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910805116583936 |
|---|---|
| author | He, Guang Ping |
| author_facet | He, Guang Ping |
| contents | Finding gradients is a crucial step in training machine learning models. For quantum neural networks, computing gradients using the parameter-shift rule requires calculating the cost function twice for each adjustable parameter in the network. When the total number of parameters is large, the quantum circuit must be repeatedly adjusted and executed, leading to significant computational overhead. Here we propose an approach to compute all gradients using a single circuit only, significantly reducing both the circuit depth and the number of classical registers required. We experimentally validate our approach on both quantum simulators and IBM's real quantum hardware, demonstrating that our method significantly reduces circuit compilation time compared to the conventional approach, resulting in a substantial speedup in total runtime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2307_08167 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Computing the gradients with respect to all parameters of a quantum neural network using a single circuit He, Guang Ping Quantum Physics Artificial Intelligence Machine Learning Finding gradients is a crucial step in training machine learning models. For quantum neural networks, computing gradients using the parameter-shift rule requires calculating the cost function twice for each adjustable parameter in the network. When the total number of parameters is large, the quantum circuit must be repeatedly adjusted and executed, leading to significant computational overhead. Here we propose an approach to compute all gradients using a single circuit only, significantly reducing both the circuit depth and the number of classical registers required. We experimentally validate our approach on both quantum simulators and IBM's real quantum hardware, demonstrating that our method significantly reduces circuit compilation time compared to the conventional approach, resulting in a substantial speedup in total runtime. |
| title | Computing the gradients with respect to all parameters of a quantum neural network using a single circuit |
| topic | Quantum Physics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2307.08167 |