Training parameterized quantum circuits by gradually adding reuploader blocks, rather than using fixed depth from the start, reduces loss and variance on the tested regression and PDE tasks.
Layerwise learning for quantum neural networks,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quantum Circuit Training with Growth-Based Architectures
Training parameterized quantum circuits by gradually adding reuploader blocks, rather than using fixed depth from the start, reduces loss and variance on the tested regression and PDE tasks.