Newton-Schulz Retraction-Based Inference Enables Hidden Quantum Markov Models to Outperform Classical HMMs

• URL: http://arxiv.org/abs/2608.06554v1
• Date: Thu, 06 Aug 2026 20:11:55 GMT
• Title: Newton-Schulz Retraction-Based Inference Enables Hidden Quantum Markov Models to Outperform Classical HMMs
• Abstract summary: We introduce NS-RIS, Newton--Schulz Retraction-based Inference on the Stiefel manifold, a scalable algorithm for learning trace-preserving HQMMs.<n>On synthetic benchmarks, NS-RIS outperforms both Expectation--Maximization (EM)-trained HMMs and the state-of-the-art HQMM COSM.<n>These results move HQMMs beyond a theoretical generalization and establish them as practical and expressive models for scientific sequence data.
• Score: 0.7493761475572844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hidden Markov models (HMMs) are widely used probabilistic models for discrete sequential data but can be limited when hidden dynamics are complex. Hidden quantum Markov models (HQMMs) generalize HMMs by replacing probability vectors with density matrices and stochastic transitions with quantum operations, enabling richer latent representations. However, existing HQMM learning methods have not consistently outperformed Expectation--Maximization (EM)-trained HMMs on data not generated by quantum processes, limiting their practical applicability. We introduce NS-RIS, Newton--Schulz Retraction-based Inference on the Stiefel manifold, a scalable algorithm for learning trace-preserving HQMMs. NS-RIS uses Newton--Schulz orthogonalization to compute a polar-factor search direction while preserving Stiefel-manifold feasibility, avoiding costly matrix decompositions. We further establish a finite-time stationarity guarantee under standard assumptions on smoothness, stochastic gradients, and finite Newton--Schulz accuracy. Empirically, NS-RIS provides the first benchmark evidence that an HQMM can significantly outperform an EM-trained HMM on data not generated by a quantum model. On synthetic HMM-generated benchmarks, NS-RIS outperforms both EM and the state-of-the-art HQMM method COSM, improving the evaluation metric by an average of 38.5% and by up to 50.6%. On a synthetic HQMM benchmark, it improves the test metric over COSM by 18.9% while reducing runtime by 12.0%. On the real-world Splice classification benchmark, NS-RIS also surpasses both EM and COSM in higher-dimensional latent regimes, reducing mean classification error by 17.9% for latent dimension 6 and 14.9% for latent dimension 8 relative to COSM. These results move HQMMs beyond a theoretical generalization of HMMs and establish them as practical and expressive models for scientific sequence data.

Related papers

• Quantum-Enhanced Synthetic Data Generation Using Quantum Circuit Born Machines for Imbalanced Tabular Learning [0.0]
  We present a quantum-classical framework for synthetic data generation using a Quantum Circuit Born Machine (QCBM)<n>The proposed approach exploits quantum mechanical properties -- superposition and entanglement -- within a parameterized variational quantum circuit.<n>We show that QCBM achieves competitive classification performance and produces lower Mean Maximum Discrepancy (MMD) on the Telco dataset.
  arXiv  Detail & Related papers  (2026-07-10T05:53:29Z)
• Quantum Dimension Reduction of Hidden Markov Models [0.0]
  We introduce a pipeline by which emphany finite, ergodic HMM can be compressed.<n>We demonstrate the method on both a simple toy model, and on a speech-derived HMM trained from data.
  arXiv  Detail & Related papers  (2026-01-22T17:27:52Z)
• Robust Iterative Learning Hidden Quantum Markov Models [0.7493761475572844]
  Hidden Quantum Markov Models (HQMMs) extend classical Hidden Markov Models to the quantum domain.<n>Existing HQMM learning algorithms are sensitive to data corruption and lack mechanisms to ensure robustness under adversarial perturbations.<n>We introduce the Adversarially Corrupted HQMM, which formalizes robustness analysis by allowing a controlled fraction of observation sequences to be adversarially corrupted.
  arXiv  Detail & Related papers  (2025-10-27T11:48:44Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• QKSAN: A Quantum Kernel Self-Attention Network [53.96779043113156]
  A Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. A Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques. Four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST.
  arXiv  Detail & Related papers  (2023-08-25T15:08:19Z)
• A new quantum machine learning algorithm: split hidden quantum Markov model inspired by quantum conditional master equation [14.262911696419934]
  We introduce the split HQMM (SHQMM) for implementing the hidden quantum Markov process. Experimental results suggest our model outperforms previous models in terms of scope of applications and robustness.
  arXiv  Detail & Related papers  (2023-07-17T16:55:26Z)
• Learning Hidden Markov Models When the Locations of Missing Observations are Unknown [54.40592050737724]
  We consider the general problem of learning an HMM from data with unknown missing observation locations. We provide reconstruction algorithms that do not require any assumptions about the structure of the underlying chain. We show that under proper specifications one can reconstruct the process dynamics as well as if the missing observations positions were known.
  arXiv  Detail & Related papers  (2022-03-12T22:40:43Z)
• Learning Circular Hidden Quantum Markov Models: A Tensor Network Approach [34.77250498401055]
  We show that c-HQMMs are equivalent to a constrained tensor network. This equivalence enables us to provide an efficient learning model for c-HQMMs. The proposed learning approach is evaluated on six real datasets.
  arXiv  Detail & Related papers  (2021-10-29T23:09:31Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)
• DenseHMM: Learning Hidden Markov Models by Learning Dense Representations [0.0]
  We propose a modification of Hidden Markov Models (HMMs) that allows to learn dense representations of both the hidden states and the observables. Compared to the standard HMM, transition probabilities are not atomic but composed of these representations via kernelization. The properties of the DenseHMM like learned co-occurrences and log-likelihoods are studied empirically on synthetic and biomedical datasets.
  arXiv  Detail & Related papers  (2020-12-17T17:48:27Z)
• Scaling Hidden Markov Language Models [118.55908381553056]
  This work revisits the challenge of scaling HMMs to language modeling datasets. We propose methods for scaling HMMs to massive state spaces while maintaining efficient exact inference, a compact parameterization, and effective regularization.
  arXiv  Detail & Related papers  (2020-11-09T18:51:55Z)
• Q-GADMM: Quantized Group ADMM for Communication Efficient Decentralized Machine Learning [66.18202188565922]
  We propose a communication-efficient decentralized machine learning (ML) algorithm, coined QGADMM (QGADMM)<n>We develop a novel quantization method to adaptively adjust modelization levels and their probabilities, while proving the convergence of QGADMM for convex functions.
  arXiv  Detail & Related papers  (2019-10-23T10:47:06Z)

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.