Quantum Tilted Loss in Variational Optimization: Theory and Applications

• URL: http://arxiv.org/abs/2605.02850v1
• Date: Mon, 04 May 2026 17:25:43 GMT
• Title: Quantum Tilted Loss in Variational Optimization: Theory and Applications
• Abstract summary: We introduce the Quantum Tilted Loss (QTL) to reshape the optimization landscape.<n>QTL can amplify gradient signals in structured settings while preserving the problem's true global minima.<n>We formalize this trainability-estimability trade-off, demonstrating how aggressive tilting fundamentally shifts the optimization bottleneck.
• Score: 2.274915755738124
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Variational quantum algorithms (VQAs) are leading strategies for using near-term quantum devices, with a well-studied bottleneck being their trainability. Standard expectation-value objectives with expressive circuits frequently encounter barren plateaus in the optimization landscape during training. To address this challenge, we introduce the Quantum Tilted Loss (QTL), an operator-level generalization of classical exponential tilting designed to systematically reshape the optimization landscape. By tuning a single continuous parameter, QTL can amplify gradient signals in structured settings while preserving the problem's true global minima. We provide a theoretical foundation that unifies standard expectation minimization with popular tunable heuristics, such as Conditional Value-at-Risk (CVaR) and Gibbs formulations. Deploying this framework requires balancing the geometric benefits of a sharpened landscape against the statistical cost of estimating nonlinear gradients from finite quantum measurements. We formalize this trainability-estimability trade-off, demonstrating how aggressive tilting fundamentally shifts the optimization bottleneck from landscape flatness to sample complexity. Thus, the operational bottleneck shifts from vanishing gradients to measurement sampling variance. Finally, we exhibit through numerical simulations that ascending tilt schedules can outperform fixed-tilt training in finite-shot regimes.

Related papers

• Stochastic Pauli-path simulator for large-scale quantum optimization [57.179828941706006]
  Pauli-path simulators offer a promising route to large-scale classical simulation of quantum circuits in the low-magic regime.<n>Existing approaches either lack native support for gradient-based optimization or suffer from severe gradient bias.<n>Here we propose the Pauli-path simulator (SPPS), a computational framework for large-scale quantum optimization.
  arXiv  Detail & Related papers  (2026-07-20T10:43:44Z)
• Adaptive directional gradients for parameterised quantum circuits [1.5549963606717787]
  Training parameterised quantum circuits (PQCs) on quantum hardware is bottlenecked by the measurement cost of gradient estimation.<n>We propose a framework of forward gradient estimators for PQCs, based on the forward mode of automatic differentiation.<n>We show numerically that forward optimisation train Hamming-weight-preserving quantum neural networks with up to 60 qubits and 1770 parameters more efficiently than the parameter-shift rule.
  arXiv  Detail & Related papers  (2026-06-08T16:59:58Z)
• High-Precision Variational Quantum SVD via Classical Orthogonality Correction [0.0]
  We introduce a hybrid quantum-classical variational framework for partial singular value decomposition of bipartite states.<n>We employ a deflation-based optimization approach to sequentially extract dominant and subdominant Schmidt components of target states.<n>Our framework provides a robust pathway for large-scale entanglement spectrum estimation on advanced near-term quantum devices.
  arXiv  Detail & Related papers  (2026-05-09T04:49:05Z)
• Trainability-Oriented Hybrid Quantum Regression via Geometric Preconditioning and Curriculum Optimization [0.6445605125467574]
  Quantum neural networks (QNNs) have attracted growing interest for scientific machine learning.<n>In regression settings they often suffer from limited trainability under noisy gradients and ill-conditioned optimization.<n>We propose a hybrid quantum-classical regression framework designed to mitigate these bottlenecks.
  arXiv  Detail & Related papers  (2026-01-17T07:32:18Z)
• 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)
• Escaping Barren Plateaus in Variational Quantum Algorithms Using Negative Learning Rate in Quantum Internet of Things [8.98664000532717]
  Variational Quantum Algorithms (VQAs) are becoming the primary computational primitive for next-generation quantum computers.<n>Under device-constrained execution conditions, the scalability of learning is severely limited by barren plateaus.<n>We present a novel approach for escaping barren plateaus by including negative learning rates into the optimization process.
  arXiv  Detail & Related papers  (2025-11-28T03:32:33Z)
• LOTION: Smoothing the Optimization Landscape for Quantized Training [9.855789447735757]
  We introduce LOTION, a principled smoothing framework that replaces the raw quantized loss with its expectation under unbiased randomized-rounding noise.<n>We empirically demonstrate that this method outperforms standard QAT on synthetic testbeds and on 150M- and 300M- parameter language models.
  arXiv  Detail & Related papers  (2025-10-09T19:16:46Z)
• Neural Optimal Transport Meets Multivariate Conformal Prediction [58.43397908730771]
  We propose a framework for conditional vectorile regression (CVQR)<n>CVQR combines neural optimal transport with quantized optimization, and apply it to predictions.
  arXiv  Detail & Related papers  (2025-09-29T19:50:19Z)
• Sculpting Quantum Landscapes: Fubini-Study Metric Conditioning for Geometry Aware Learning in Parameterized Quantum Circuits [0.0]
  We present a novel meta learning framework called Sculpture that explicitly conditions the Fubini Study metric tensor to mitigate barren plateaus in variational quantum algorithms.<n>Our theoretical analysis identifies the logarithmic condition number of the Fubini Study metric as a critical geometric quantity governing trainability, optimization dynamics, and generalization.
  arXiv  Detail & Related papers  (2025-06-27T06:30:33Z)
• FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation [55.12070409045766]
  Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years.<n>Current PTQ methods for Vision Transformers (ViTs) still suffer from significant accuracy degradation, especially under low-bit quantization.
  arXiv  Detail & Related papers  (2025-06-13T07:57:38Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)
• Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training [99.42912552638168]
  Communication of gradients is costly for training deep neural networks with multiple devices in computer vision applications. In this work, we deduce the optimal condition of both the binary and multi-level gradient quantization for textbfANY gradient distribution. Based on the optimal condition, we develop two novel quantization schemes: biased BinGrad and unbiased ORQ for binary and multi-level gradient quantization respectively.
  arXiv  Detail & Related papers  (2020-02-25T18:28:39Z)
• Gradient $\ell_1$ Regularization for Quantization Robustness [70.39776106458858]
  We derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our approach enables storing a single set of weights that can be quantized on-demand to different bit-widths.
  arXiv  Detail & Related papers  (2020-02-18T12:31:34Z)

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.