Barren plateaus in quantum neural network training landscapes
Gradient-based hybrid quantum-classical algorithms are often initialised with random, unstructured guesses. Here, the authors show that this approach will fail in the long run, due to the exponentially-small probability of finding a large enough gradient along any direction.
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
Nature Portfolio
2018-11-01
|
| Serie: | Nature Communications |
| Accesso online: | https://doi.org/10.1038/s41467-018-07090-4 |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|