← Back to all news
arXiv Machine Learning By Nayan D'Souza, Christopher J. Agostino

SPSA Hyperparameter Tuning for Variational Quantum Natural Language Inference

Read the original on arXiv Machine Learning →

The paper investigates how to tune the hyperparameters of simultaneous perturbation stochastic approximation (SPSA) for training a 6‑qubit, 60‑parameter variational quantum natural language inference (QNLI) classifier. By exploring a broad grid of perturbation scales, learning rates, and gain‑decay schedules, the authors found that an AdamW‑style SPSA configuration (c₀=0.01, η=0.10, γ=0.10) achieved 55 % ± 11 % test accuracy, improving over the default SPSA but still 16–19 percentage points below parameter‑shift baselines. Classical‑gain SPSA and Bures‑preconditioned SPSA performed worse, with accuracies of 51 % and 46 % respectively, indicating that two‑sample SPSA gradients suffer from high variance when optimizing many parameters over limited epochs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Jun 9

Adaptive directional gradients for parameterised quantum circuits

arXiv:2606. 09734v1 Announce Type: cross Abstract: Training parameterised quantum circuits (PQCs) on quantum hardware is bottlenecked by the measurement cost of gradient estimation, which under the parameter-shift rule scales linearly in the number of trainable parameters and dominates the total shot budget of training at scale.

By Brian Coyle, Snehal Raj, Virag Umathe, El Amine Cherrat, Elham Kashefi
More like this →
arXiv Machine Learning
Jun 24

Quantum Adaptive Self-Attention for Quantum Transformer Models

arXiv:2504. 05336v4 Announce Type: replace-cross Abstract: A recurring weakness in quantum machine learning (QML) is that reported ``quantum advantages'' are seldom tested against a \emph{capacity-matched} classical control, leaving it unclear whether a gain comes from the quantum substrate or from the architectural change that accompanies it.

By Chi-Sheng Chen, En-Jui Kuo
llmsbenchmarks
More like this →
arXiv Machine Learning
Sep 22

Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States

The paper investigates how stochastic reconfiguration (SR), the standard optimizer for neural quantum states (NQS), functions as a statistical filter in overparameterized regimes where parameters outnumber Monte Carlo samples. By interpreting SR as ridge regression on tangent features, the authors show that the diagonal shift balances useful update directions against variance from fitting finite-sample residuals, leading to a U-shaped validation risk curve. They introduce multi-shift SR (MS‑SR), which averages ridge solutions at data‑adaptive shifts, and demonstrate that it reduces validation risk and update variance compared to fixed‑shift SR in both small and large system experiments.

By Tak Hur
benchmarks
More like this →
arXiv Machine Learning
Sep 7

Impact of Data Loss in Postprocessing on Training and Inference of Quantum Neural Networks

The paper investigates how postprocessing routines in quantum neural network software can cause significant data loss when run on large quantum hardware. In a case study of Qiskit’s “SamplerQNN”, a filter that assumes measurement bit‑strings are in virtual qubit space removed 85–99.6% of valid shots on IBM backends, leading to unnormalised probability vectors and distorted predictions. This loss caused inference accuracy to drop from 0.94 to 0.39 and compressed training loss signals by 22–27×, severely reducing optimizer sensitivity. The authors implemented a layout‑based marginalisation fix that was merged into the library to make “SamplerQNN” forward‑compatible with current and future hardware.

By Soraya V. Panambalom, Edoardo Altamura, Nick Chancellor, Jonte R. Hance
More like this →