SAFE Quantum Machine Learning with Variational Quantum Classifiers

• URL: http://arxiv.org/abs/2605.16067v1
• Date: Fri, 15 May 2026 15:29:36 GMT
• Title: SAFE Quantum Machine Learning with Variational Quantum Classifiers
• Abstract summary: We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding.<n>The resulting model induces a structured and smooth hypothesis class with controlled sensitivity to input variations.<n>Model reliability is assessed using SAFE-AI metrics derived from the Cramer von Mises divergence.
• Score: 6.49395734735121
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a variational quantum classifier operating on high dimensional deep representations via amplitude encoding, stabilized by a learnable classical pre encoding layer.By combining normalized amplitude embeddings with bounded quantum observables, the resulting model induces a structured and smooth hypothesis class with controlled sensitivity to input variations. Model reliability is assessed using SAFE-AI metrics derived from the Cramer von Mises divergence, enabling consistent evaluation across accuracy, robustness, and explainability dimensions. Empirical results show that the proposed quantum model provides competitive predictive performance compared with strong classical baselines while exhibiting a more balanced SAFE reliability profile, with improved robustness to noise and stability under structured feature removal. These findings suggest that variational quantum circuits offer a principled mechanism for stability oriented SAFE learning in safety critical settings.

Related papers

• Reliability Scaling Laws for Quantized Large Language Models [68.39028482878265]
  Quantization is a strategy to build capable and resource-efficient large language models (LLMs) by reducing the bitwidth of the parameters.<n>We first conduct a comprehensive reliability evaluation of quantized LLMs consisting of three key components.<n>A reliability peak occurs for 4-bit quantized models, indicating that quantizing moderately sized models offers the best reliability-efficiency trade-off.
  arXiv  Detail & Related papers  (2026-07-12T17:39:09Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Stabilized Maximum-Likelihood Iterative Quantum Amplitude Estimation for Structural CVaR under Correlated Random Fields [0.0]
  Conditional Value-at-Risk (CVaR) is a central tail-risk measure in structural mechanics.<n>We develop a quantum-enhanced inference framework that casts CVaR evaluation as a confidence-constrained maximum-likelihood amplitude estimation problem.
  arXiv  Detail & Related papers  (2026-02-10T14:53:26Z)
• Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing [68.35481158940401]
  CL-QAS is a continual quantum architecture search framework.<n>It mitigates challenges of costly encoding amplitude and forgetting in variational quantum circuits.<n>It achieves controllable robustness expressivity, sample-efficient generalization, and smooth convergence without barren plateaus.
  arXiv  Detail & Related papers  (2026-01-10T02:36:03Z)
• Robust Causal Directionality Inference in Quantum Inference under MNAR Observation and High-Dimensional Noise [0.0]
  In quantum mechanics, observation actively shapes the system, paralleling the statistical notion of Missing Not At Random (MNAR)<n>This study introduces a unified framework for causal directionality inference in quantum engineering.
  arXiv  Detail & Related papers  (2025-12-18T05:26:25Z)
• Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Era [3.1351527202068445]
  This research offers a broad roadmap for Trustworthy Quantum Machine Learning (TQML)<n>It integrates three foundational pillars of reliability: (i) uncertainty quantification for calibrated and risk-aware decision making, (ii) robustness adversarial against classical and quantum-native threat models, and (iii) privacy preservation in distributed and delegated quantum learning scenarios.<n>This roadmap seeks to define trustworthiness as a first-class design objective for quantum AI.
  arXiv  Detail & Related papers  (2025-11-04T14:24:17Z)
• Contrastive Knowledge Transfer and Robust Optimization for Secure Alignment of Large Language Models [9.353236468990945]
  This paper addresses the limitations of large-scale language models in safety alignment and robustness.<n>It proposes a fine-tuning method that combines contrastive distillation with noise-robust training.<n>Results show that the method significantly outperforms existing baselines in knowledge transfer, robustness, and overall safety.
  arXiv  Detail & Related papers  (2025-10-31T00:54:33Z)
• TensorHyper-VQC: A Tensor-Train-Guided Hypernetwork for Robust and Scalable Variational Quantum Computing [50.95799256262098]
  We introduceHyper-VQC, a novel tensor-train (TT)-guided hypernetwork framework for quantum machine learning.<n>Our framework delegates the generation of quantum circuit parameters to a classical TT network, effectively decoupling optimization from quantum hardware.<n>These results positionHyper-VQC as a scalable and noise-resilient framework for advancing practical quantum machine learning on near-term devices.
  arXiv  Detail & Related papers  (2025-08-01T23:37:55Z)
• Dynamic Estimation Loss Control in Variational Quantum Sensing via Online Conformal Inference [39.72602887300498]
  Current variational quantum sensing methods lack rigorous performance guarantees.<n>This paper proposes an online control framework for VQS that dynamically updates the variational parameters while providing deterministic error bars on the estimates.<n> Experiments on a quantum magnetometry task confirm that the proposed dynamic VQS approach maintains the required reliability over time, while still yielding precise estimates.
  arXiv  Detail & Related papers  (2025-05-29T12:19:07Z)
• Federated Conformal Predictors for Distributed Uncertainty Quantification [83.50609351513886]
  Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning. In this paper, we extend conformal prediction to the federated learning setting. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction framework.
  arXiv  Detail & Related papers  (2023-05-27T19:57:27Z)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty [68.00748155945047]
  Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. Our contribution is a novel abstraction-based controller method for continuous-state models with noise, uncertain parameters, and external disturbances.
  arXiv  Detail & Related papers  (2022-10-12T07:57:03Z)
• Probabilistic robust linear quadratic regulators with Gaussian processes [73.0364959221845]
  Probabilistic models such as Gaussian processes (GPs) are powerful tools to learn unknown dynamical systems from data for subsequent use in control design. We present a novel controller synthesis for linearized GP dynamics that yields robust controllers with respect to a probabilistic stability margin.
  arXiv  Detail & Related papers  (2021-05-17T08:36:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.