Sums of trainable parametrised circuits remain trainable, with explicit variance formulas for LCU states under Haar-random assumptions.
On the sample complexity of quantum boltzmann machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Trainability of Parametrised Linear Combinations of Unitaries
Sums of trainable parametrised circuits remain trainable, with explicit variance formulas for LCU states under Haar-random assumptions.