Empirical Sample Complexity of Neural Network Mixed State Reconstruction

被引:0
|
作者
Zhao, Haimeng [1 ,2 ,3 ]
Carleo, Giuseppe [1 ,2 ]
Vicentini, Filippo [1 ,2 ,4 ,5 ]
机构
[1] Ecole Polytech Fed Lausanne EPFL, Inst Phys, CH-1015 Lausanne, Switzerland
[2] Ecole Polytech Fed Lausanne EPFL, Ctr Quantum Sci & Engn, CH-1015 Lausanne, Switzerland
[3] Tsinghua Univ, Zhili Coll, Beijing 100084, Peoples R China
[4] Ecole Polytech, Inst Polytech Paris, CPHT, CNRS, F-91120 Palaiseau, France
[5] Univ PSL, Coll France, 11 Pl Marcelin Berthelot, F-75005 Paris, France
来源
QUANTUM | 2024年 / 8卷
关键词
D O I
暂无
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Quantum state reconstruction using Neural Quantum States has been proposed as a viable tool to reduce quantum shot complexity in practical applications, and its advantage over competing techniques has been shown in numerical experiments focusing mainly on the noiseless case. In this work, we numerically investigate the performance of different quantum state reconstruction techniques for mixed states: the finite-temperature Ising model. We show how to systematically reduce the quantum resource requirement of the algorithms by applying variance reduction techniques. Then, we compare the two leading neural quantum state encodings of the state, namely, the Neural Density Operator and the positive operator-valued measurement representation, and illustrate their different performance as the mixedness of the target state varies. We find that certain encodings are more efficient in different regimes of mixedness and point out the need for designing more efficient encodings in terms of both classical and quantum resources.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Empirical study on generalization capability of neural networks with respective to network complexity
    Park, S
    Park, C
    [J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 647 - 650
  • [2] On the sample complexity for neural trees
    Schmitt, M
    [J]. ALGORITHMIC LEARNING THEORY, 1998, 1501 : 375 - 384
  • [3] On the sample complexity for nonoverlapping neural networks
    Schmitt, M
    [J]. MACHINE LEARNING, 1999, 37 (02) : 131 - 141
  • [4] On the Sample Complexity for Nonoverlapping Neural Networks
    Michael Schmitt
    [J]. Machine Learning, 1999, 37 : 131 - 141
  • [5] Bounds on the complexity of recurrent neural network implementations of finite state machines
    NEC Research Institute, 4 Independence Way, Princeton, NJ 08540, United States
    [J]. NEURAL NETW., 2 (243-252):
  • [6] Bounds on the complexity of recurrent neural network implementations of finite state machines
    Horne, BG
    Hush, DR
    [J]. NEURAL NETWORKS, 1996, 9 (02) : 243 - 252
  • [7] The Influence of Sample Reconstruction on Stock Trend Prediction via NARX Neural Network
    Wei, Yi
    Chaudhary, Vipin
    [J]. 2015 IEEE 14TH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA), 2015, : 52 - 57
  • [8] Mixed Quantum State Dynamics Estimation with Artificial Neural Network
    Kim, Changjun
    Rhee, June-Koo Kevin
    Lee, Woojun
    Ahn, Jaewook
    [J]. 2018 INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGY CONVERGENCE (ICTC), 2018, : 740 - 747
  • [9] Sample Complexity and Overparameterization Bounds for Temporal-Difference Learning With Neural Network Approximation
    Cayci, Semih
    Satpathi, Siddhartha
    He, Niao
    Srikant, R.
    [J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (05) : 2891 - 2905
  • [10] Brain model state space reconstruction using an LSTM neural network
    Liu, Yueyang
    Soto-Breceda, Artemio
    Karoly, Philippa
    Grayden, David B.
    Zhao, Yun
    Cook, Mark J.
    Schmidt, Daniel
    Kuhlmann, Levin
    [J]. JOURNAL OF NEURAL ENGINEERING, 2023, 20 (03)