AdaInit uses LLMs with submartingale properties to iteratively synthesize QNN initial parameters that maintain non-negligible gradient variance and mitigate barren plateaus, with claimed theoretical convergence guarantees and empirical outperformance.
Normalized gradient descent for variational quantum algorithms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Large Language Models Can Help Mitigate Barren Plateaus in Quantum Neural Networks
AdaInit uses LLMs with submartingale properties to iteratively synthesize QNN initial parameters that maintain non-negligible gradient variance and mitigate barren plateaus, with claimed theoretical convergence guarantees and empirical outperformance.