Barren plateaus in quantum neural network training landscapes
oleh: Jarrod R. McClean, Sergio Boixo, Vadim N. Smelyanskiy, Ryan Babbush, Hartmut Neven
| Format: | Article |
|---|---|
| Diterbitkan: | Nature Portfolio 2018-11-01 |
Deskripsi
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.