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.
Probability with martingales
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Provides Hessian-based theoretical characterizations of SGD dynamics and a scale-invariant generalization bound for deep nets, backed by experiments on synthetic data, MNIST, and CIFAR-10.
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.
-
Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
Provides Hessian-based theoretical characterizations of SGD dynamics and a scale-invariant generalization bound for deep nets, backed by experiments on synthetic data, MNIST, and CIFAR-10.