Neural Network Assisted Fermionic Compression Encoding: A Lossy-QSCI Framework for Scalable Quantum Chemistry Simulations

• URL: http://arxiv.org/abs/2505.17846v1
• Date: Fri, 23 May 2025 13:00:16 GMT
• Title: Neural Network Assisted Fermionic Compression Encoding: A Lossy-QSCI Framework for Scalable Quantum Chemistry Simulations
• Authors: Yu-cheng Chen, Ronin Wu, M. H. Cheng, Min-Hsiu Hsieh,
• Abstract summary: Quantum computing promises to revolutionize many-body simulations for quantum chemistry, but its potential is constrained by limited qubits and noise in current devices.<n>We introduce the Lossy Quantum Selected Configuration Interaction (Lossy-QSCI) framework, which combines a lossy subspace Hamiltonian preparation with a generic QSCI selection process.<n>This framework integrates a chemistry-inspired lossy Random Linear pipeline with a neural network-assisted Fermionic Expectation Decoder (NN-FED)
• Score: 11.823527250715971
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantum computing promises to revolutionize many-body simulations for quantum chemistry, but its potential is constrained by limited qubits and noise in current devices. In this work, we introduce the Lossy Quantum Selected Configuration Interaction (Lossy-QSCI) framework, which combines a lossy subspace Hamiltonian preparation pipeline with a generic QSCI selection process. This framework integrates a chemistry-inspired lossy Random Linear Encoder (Chemical-RLE) with a neural network-assisted Fermionic Expectation Decoder (NN-FED). The RLE leverages fermionic number conservation to compress quantum states, reducing qubit requirements to O(N log M) for M spin orbitals and N electrons, while preserving crucial ground state information and enabling self-consistent configuration recovery. NN-FED, powered by a neural network trained with minimal data, efficiently decodes these compressed states, overcoming the measurement challenges common in the approaches of the traditional QSCI and its variants. Through iterative quantum sampling and classical post-processing, our hybrid method refines ground state estimates with high efficiency. Demonstrated on the C2 and LiH molecules, our framework achieves chemical accuracy with fewer qubits and basis states, paving a scalable pathway for quantum chemistry simulations on both near-term and fault-tolerant quantum hardware.

Related papers

• Coupled Cluster Downfolding Theory in Simulations of Chemical Systems on Quantum Hardware [9.389379035303165]
  We show how classical resources are used to construct effective Hamiltonians characterized by dimensions that conform to the constraints of current quantum devices.<n>We argue that such flexible hybrid algorithms, where problem size can be tailored to available quantum resources, can serve as a bridge between noisy intermediate-scale quantum (QNIS) devices and future fault-tolerant quantum computers.
  arXiv  Detail & Related papers  (2025-07-01T21:34:29Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [60.996803677584424]
  Variational Quantum Circuits (VQCs) offer a novel pathway for quantum machine learning.<n>Their practical application is hindered by inherent limitations such as constrained linear expressivity, optimization challenges, and acute sensitivity to quantum hardware noise.<n>This work introduces VQC-MLPNet, a scalable and robust hybrid quantum-classical architecture designed to overcome these obstacles.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• Efficient Hamiltonian Simulation: A Utility Scale Perspective for Covalent Inhibitor Reactivity Prediction [0.25111276334134786]
  Quantum computing applications in the noisy intermediate-scale quantum (NISQ) era require algorithms that can generate shallower circuits feasible for today's quantum systems.<n>This is particularly challenging for quantum chemistry applications due to the inherent complexity of molecular systems.<n>We demonstrate a systematic circuit reduction approach for scaling to larger active spaces, while maintaining sufficient accuracy for molecular reactivity predictions using the Quantum-Centric Data-Driven R&D framework.
  arXiv  Detail & Related papers  (2024-12-20T11:25:01Z)
• Demonstration of a variational quantum eigensolver with a solid-state spin system under ambient conditions [15.044543674753308]
  Quantum simulators offer the potential to utilize the quantum nature of a physical system to study another physical system. The variational-quantum-eigensolver algorithm is a particularly promising application for investigating molecular electronic structures. Spin-based solid-state qubits have the advantage of long decoherence time and high-fidelity quantum gates.
  arXiv  Detail & Related papers  (2024-07-23T09:17:06Z)
• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity [50.387179833629254]
  We introduce a collaborative classical-quantum architecture called co-TenQu. Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
  arXiv  Detail & Related papers  (2024-02-23T14:09:41Z)
• Towards Neural Variational Monte Carlo That Scales Linearly with System Size [67.09349921751341]
  Quantum many-body problems are central to demystifying some exotic quantum phenomena, e.g., high-temperature superconductors. The combination of neural networks (NN) for representing quantum states, and the Variational Monte Carlo (VMC) algorithm, has been shown to be a promising method for solving such problems. We propose a NN architecture called Vector-Quantized Neural Quantum States (VQ-NQS) that utilizes vector-quantization techniques to leverage redundancies in the local-energy calculations of the VMC algorithm.
  arXiv  Detail & Related papers  (2022-12-21T19:00:04Z)
• QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks [124.7972093110732]
  We propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations. To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections. Our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets.
  arXiv  Detail & Related papers  (2022-11-09T21:43:16Z)
• Realizing Quantum Convolutional Neural Networks on a Superconducting Quantum Processor to Recognize Quantum Phases [2.1465372441653354]
  Quantum neural networks tailored to recognize specific features of quantum states by combining unitary operations, measurements and feedforward promise to require fewer measurements and to tolerate errors. We realize a quantum convolutional neural network (QCNN) on a 7-qubit superconducting quantum processor to identify symmetry-protected topological phases of a spin model characterized by a non-zero string order parameter. We find that, despite being composed of finite-fidelity gates itself, the QCNN recognizes the topological phase with higher fidelity than direct measurements of the string order parameter for the prepared states.
  arXiv  Detail & Related papers  (2021-09-13T12:32:57Z)
• An Algebraic Quantum Circuit Compression Algorithm for Hamiltonian Simulation [55.41644538483948]
  Current generation noisy intermediate-scale quantum (NISQ) computers are severely limited in chip size and error rates. We derive localized circuit transformations to efficiently compress quantum circuits for simulation of certain spin Hamiltonians known as free fermions. The proposed numerical circuit compression algorithm behaves backward stable and scales cubically in the number of spins enabling circuit synthesis beyond $mathcalO(103)$ spins.
  arXiv  Detail & Related papers  (2021-08-06T19:38:03Z)
• On exploring the potential of quantum auto-encoder for learning quantum systems [60.909817434753315]
  We devise three effective QAE-based learning protocols to address three classically computational hard learning problems. Our work sheds new light on developing advanced quantum learning algorithms to accomplish hard quantum physics and quantum information processing tasks.
  arXiv  Detail & Related papers  (2021-06-29T14:01:40Z)
• Towards a NISQ Algorithm to Simulate Hermitian Matrix Exponentiation [0.0]
  A practical fault-tolerant quantum computer is worth looking forward to as it provides applications that outperform their known classical counterparts. It would take decades to make it happen, exploiting the power of noisy intermediate-scale quantum(NISQ) devices, which already exist, is becoming one of current goals. In this article, a method is reported as simulating a hermitian matrix exponentiation using parametrized quantum circuit.
  arXiv  Detail & Related papers  (2021-05-28T06:37:12Z)
• Simulating quantum chemistry in the seniority-zero space on qubit-based quantum computers [0.0]
  We combine the so-called seniority-zero, or paired-electron, approximation of computational quantum chemistry with techniques for simulating molecular chemistry on gate-based quantum computers. We show that using the freed-up quantum resources for increasing the basis set can lead to more accurate results and reductions in the necessary number of quantum computing runs.
  arXiv  Detail & Related papers  (2020-01-31T19:44:37Z)
• Entanglement Classification via Neural Network Quantum States [58.720142291102135]
  In this paper we combine machine-learning tools and the theory of quantum entanglement to perform entanglement classification for multipartite qubit systems in pure states. We use a parameterisation of quantum systems using artificial neural networks in a restricted Boltzmann machine (RBM) architecture, known as Neural Network Quantum States (NNS)
  arXiv  Detail & Related papers  (2019-12-31T07:40:23Z)

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.