Making Neural Networks More Suitable for Approximate Clifford+T Circuit Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910916577067008 |
|---|---|
| author | Weiden, Mathias Kalloor, Justin Kubiatowicz, John Iancu, Costin |
| author_facet | Weiden, Mathias Kalloor, Justin Kubiatowicz, John Iancu, Costin |
| contents | Machine Learning with deep neural networks has transformed computational approaches to scientific and engineering problems. Central to many of these advancements are precisely tuned neural architectures that are tailored to the domains in which they are used. In this work, we develop deep learning techniques and architectural modifications that improve performance on reinforcement learning guided quantum circuit synthesis-the task of constructing a circuit that implements a given unitary matrix. First, we propose a global phase invariance operation which makes our architecture resilient to complex global phase shifts. Second, we demonstrate how augmenting data with small random unitary perturbations during training enables more robust learning. Finally, we show how encoding numerical data with techniques from image processing allow networks to better detect small but significant changes in data. Our work enables deep learning approaches to better synthesize quantum circuits that implement unitary matrices. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_15990 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Making Neural Networks More Suitable for Approximate Clifford+T Circuit Synthesis Weiden, Mathias Kalloor, Justin Kubiatowicz, John Iancu, Costin Quantum Physics Machine Learning with deep neural networks has transformed computational approaches to scientific and engineering problems. Central to many of these advancements are precisely tuned neural architectures that are tailored to the domains in which they are used. In this work, we develop deep learning techniques and architectural modifications that improve performance on reinforcement learning guided quantum circuit synthesis-the task of constructing a circuit that implements a given unitary matrix. First, we propose a global phase invariance operation which makes our architecture resilient to complex global phase shifts. Second, we demonstrate how augmenting data with small random unitary perturbations during training enables more robust learning. Finally, we show how encoding numerical data with techniques from image processing allow networks to better detect small but significant changes in data. Our work enables deep learning approaches to better synthesize quantum circuits that implement unitary matrices. |
| title | Making Neural Networks More Suitable for Approximate Clifford+T Circuit Synthesis |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2504.15990 |