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.
ThenT(θ)has the same distribution as|⟨u, v⟩|, whereu, vare independent, uniformly random unit vectors inR m
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
quant-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.