Artificial Intelligence · 27.08.2026, 07:48 UTC
Decomposing Gradient Suppression in Barren Plateaus: Activity, Sign Organization, and Coupling
| Schweregrad | info |
|---|---|
| Kategorie | Artificial Intelligence |
| Quelle | arXiv cs.LG ↗ |
| Veröffentlicht | 27.08.2026 UTC |
Sicherheitsmeldung mit Schweregrad noch nicht bewertet. Technische Details im Tab „Originaltext“; empfohlene Schritte in der Checkliste.
arXiv:2605.01319v2 Announce Type: replace-cross Abstract: Barren plateaus (BPs) are conventionally characterized by suppressed gradient variance, but this aggregate description does not reveal how the loss of gradient signal is composed across Hamiltonian terms. We introduce a term-resolved framework that decomposes the second moment of the gradient exactly into pre-cancellation activity, sign organization, and their statistical coupling. A conditional random-sign model, which preserves termwise magnitudes while treating signs as independent and symmetric, provides exact references for organization and coupling. We apply the framework to a hardware-efficient ansatz (HEA) and a Hamiltonian variational ansatz (HVA) for the transverse-field and longitudinal-field Ising models. For the HEA, finite-size suppression of the second moment is carried almost entirely by decaying activity, accounting for 96.5-98.9% of the fitted log-slope across tested depths in both Hamiltonians, while organization shows no systematic scaling and coupling remains consistent with its random-sign reference. For the HVA, activity and organization instead grow with system size and contribute comparably to the second-moment scaling. A bias-corrected mean-gradient check is consistent with zero in every tested condition, so these results carry over approximately to the gradient variance. Microscopic sign-alignment analysis further shows sector-structured organization in the HVA, whereas the HEA exhibits only weak residual sign structure that does not accumulate into net signed organization. These patterns …
Maßnahmen
⬇ Als MarkdownVerwandte Beiträge
- info Google Research Introduces GlucoFM: A 0.72M-Parameter Dual-Stream Foundation Model for Continuous Glucose Monitoring
- info CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
- info SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling
- info Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG