arXiv Machine Learning By Athanasios Hadjidimoulas, Tirthak Patel, Anastasios Kyrillidis

Identity-Paired Progressive Depth Training: When Trainability Persists Beyond Expressibility

Read the original on arXiv Machine Learning →

arXiv:2607. 16800v1 Announce Type: cross Abstract: Variational Quantum Algorithms (VQAs) are a leading paradigm for near-term quantum computing, yet their training suffers from sensitivity to circuit depth, initialization, and landscape pathologies such as barren plateaus.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Jul 7

Breaking the One-Dimensional Expressibility-Trainability Tradeoff

arXiv:2607. 04598v1 Announce Type: cross Abstract: Expressive parameterized quantum circuits (PQCs) are often designed under a dilemma: the growth of expressibility and entangling power (EP) that improves Hilbert-space coverage is also expected to randomize an ansatz and activate barren-plateau (BP) conditions.

By Kyoungho Cho, Yu-Seong Jeon, Jinhyoung Lee, Jeongho Bang