arXiv Machine Learning July 28, 2026 By Nikhil Khatri, Stefan Zohren, Gabriel Matos

Stacking the Deck: Tunable Trainability in Stacked LCUs

Read the original on arXiv Machine Learning →

arXiv:2607. 24686v1 Announce Type: cross Abstract: Variational quantum circuits have been central to many proposed near-term applications of quantum computing, but a growing body of evidence suggests that trainability and quantum advantage are fundamentally at odds: ans\"atze expressive enough to resist efficient classical simulation tend to exhibit barren plateaus, while structures that provably rule out barren plateaus typically render them classically simulable.

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

arXiv Machine Learning

Aug 6

Dynamical Lie Algebras Cannot Describe Shallow QAOA: Cragged Terrains, Barren Plateaus, and Empirical Hardness Models

arXiv:2608. 04252v1 Announce Type: cross Abstract: The dynamical Lie algebraic (DLA) theory of variational quantum algorithms (VQAs) predicts commonplace exponentially vanishing loss and gradient variances for sufficiently deep parametrized circuits.

By Harrison Copp, Charlton Li, An\v{z}ej Margeta-Cacace, Amy Qiao

arXiv AI

Aug 5

Separating quantum circuits from classical LLMs

arXiv:2608. 03962v1 Announce Type: cross Abstract: Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation.

By Srinivasan Arunachalam, Arkopal Dutt, Hari Krovi, Rik Sengupta

llms diffusion

Hugging Face Trending Papers

Aug 4

Separating quantum circuits from classical LLMs

Modern large language models - transformers and diffusion language models - are built around two canonical algorithmic tasks: prediction and generation. We prove unconditional separations between low-depth quantum computation and the corresponding bounded-resource classical language-model architectures in both regimes.

llms diffusion

arXiv AI

Jul 21

Long Range Frequency Tuning for QML

arXiv:2602. 23409v3 Announce Type: replace-cross Abstract: Angle-encoded variational quantum circuits admit a truncated Fourier series representation of their output, but approximating functions with maximum frequency $\omega_{\max}$ using fixed unary encoding requires $\mathcal{O}(\omega_{\max})$ encoding gates.

By Michael Poppel, Markus Baumann, Sebastian W\"olckert, Claudia Linnhoff-Popien, Jonas Stein

benchmarks

arXiv Machine Learning

Jul 17

An architectural capacity ceiling, not a barren plateau: why a fixed-encoding variational quantum circuit cannot fit the Lorenz-63 attractor

arXiv:2604. 23743v2 Announce Type: replace-cross Abstract: Variational quantum circuits train poorly on chaotic forecasting, usually blamed on barren plateaus (exponentially vanishing gradients).

By Tushar Pandey

arXiv Machine Learning

Jul 21

Entanglement geometry separates circuit cutting, classical hardness, and trainability

arXiv:2607. 17872v1 Announce Type: cross Abstract: Circuit cutting promises to scale quantum computations beyond current hardware, but variational quantum advantage also requires low cutting overhead, classical hardness, and trainability.

By Maria Gragera Garces, Sabina Dr\u{a}goi, Lirand\"e Pira

Related stories

Dynamical Lie Algebras Cannot Describe Shallow QAOA: Cragged Terrains, Barren Plateaus, and Empirical Hardness Models

Separating quantum circuits from classical LLMs

Separating quantum circuits from classical LLMs

Long Range Frequency Tuning for QML

An architectural capacity ceiling, not a barren plateau: why a fixed-encoding variational quantum circuit cannot fit the Lorenz-63 attractor

Entanglement geometry separates circuit cutting, classical hardness, and trainability