The trainability boundary for variational quantum objectives is the affine regime; non-affine amplification-capable losses can mitigate barren plateaus when using coarse-grained statistics at polynomial widths.
An initialization strat- egy for addressing barren plateaus in parametrized quantum circuits.Quantum, 3:214, December 2019
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
quant-ph 3verdicts
UNVERDICTED 3representative citing papers
Classical RNNs trained on small instances provide parameter initializations for QAOA and VQE that reduce total optimization iterations and generalize across problem sizes.
Topological entanglement entropy regularizes variational quantum algorithms to enforce quantum sparsity and operate at the edge of chaos for better trainability.
citing papers explorer
-
Trainability Beyond Linearity in Variational Quantum Objectives
The trainability boundary for variational quantum objectives is the affine regime; non-affine amplification-capable losses can mitigate barren plateaus when using coarse-grained statistics at polynomial widths.
-
Learning to learn with quantum neural networks via classical neural networks
Classical RNNs trained on small instances provide parameter initializations for QAOA and VQE that reduce total optimization iterations and generalize across problem sizes.
-
Quantum computation at the edge of chaos
Topological entanglement entropy regularizes variational quantum algorithms to enforce quantum sparsity and operate at the edge of chaos for better trainability.