Memory-Sample Lower Bounds for Learning with Classical-Quantum Hybrid Memory

被引:1
|
作者
Liu, Qipeng [1 ]
Raz, Ran [2 ]
Zhan, Wei [2 ]
机构
[1] Simons Inst Theory Comp, Berkeley, CA 94720 USA
[2] Princeton Univ, Princeton, NJ USA
来源
PROCEEDINGS OF THE 55TH ANNUAL ACM SYMPOSIUM ON THEORY OF COMPUTING, STOC 2023 | 2023年
基金
美国国家科学基金会;
关键词
Learning parity; Quantum lower bounds; Time-space lower bounds; EVERLASTING SECURITY;
D O I
10.1145/3564246.3585129
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In a work by Raz (J. ACM and FOCS 16), it was proved that any algorithm for parity learning on n bits requires either Omega(n(2)) bits of classical memory or an exponential number (in n) of random samples. A line of recent works continued that research direction and showed that for a large collection of classical learning tasks, either super-linear classical memory size or super-polynomially many samples are needed. All these works consider learning algorithms as classical branching programs, which perform classical computation within bounded memory. However, these results do not capture all physical computational models, remarkably, quantum computers and the use of quantum memory. It leaves the possibility that a small piece of quantum memory could significantly reduce the need for classical memory or samples and thus completely change the nature of the classical learning task. Despite the recent research on the necessity of quantum memory for intrinsic quantum learning problems like shadow tomography and purity testing, the role of quantum memory in classical learning tasks remains obscure. In this work, we study classical learning tasks in the presence of quantum memory. We prove that any quantum algorithm with both, classical memory and quantum memory, for parity learning on n bits, requires either Omega(n(2)) bits of classical memory or Omega(n) bits of quantum memory or an exponential number of samples. In other words, the memory-sample lower bound for parity learning remains qualitatively the same, even if the learning algorithm can use, in addition to the classical memory, a quantum memory of size cn (for some constant c > 0). Our result is more general and applies to many other classical learning tasks. Following previous works, we represent by the matrix M : A x X -> {-1, 1} the following learning task. An unknown x is sampled uniformly at random from a concept class X, and a learning algorithm tries to uncover x by seeing streaming of random samples (a(i), b(i) = M(a(i), x)) where for every i, a(i) is an element of A is chosen uniformly at random. Assume that k, l, r are integers such that any submatrix of M of at least 2(-k) center dot vertical bar A vertical bar rows and at least 2(-l) center dot vertical bar X vertical bar columns, has a bias of at most 2(-r). We prove that any algorithm with classical and quantum hybrid memory for the learning problem corresponding to M needs either (1) Omega(k center dot l) bits of classical memory, or (2) Omega(r) qubits of quantum memory, or (3) 2(Omega(r)) random samples, to achieve a success probability at least 2(-O(r)). Our results refute the possibility that a small amount of quantum memory significantly reduces the size of classical memory needed for efficient learning on these problems. Our results also imply improved security of several existing cryptographical protocols in the bounded-storage model (protocols that are based on parity learning on n bits), proving that security holds even in the presence of a quantum adversary with at most cn(2) bits of classical memory and cn bits of quantum memory (for some constant c > 0).
引用
收藏
页码:1097 / 1110
页数:14
相关论文
共 50 条
  • [41] Memory Bounds for Continual Learning
    Chen, Xi
    Papadimitriou, Christos
    Peng, Binghui
    2022 IEEE 63RD ANNUAL SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS), 2022, : 519 - 530
  • [42] Finite Blocklength and Moderate Deviation Analysis of Hypothesis Testing of Correlated Quantum States and Application to Classical-Quantum Channels With Memory
    Rouze, Cambyse
    Datta, Nilanjana
    IEEE TRANSACTIONS ON INFORMATION THEORY, 2018, 64 (01) : 593 - 612
  • [43] A hybrid classical-quantum approach for multi-class classification
    Avinash Chalumuri
    Raghavendra Kune
    B. S. Manoj
    Quantum Information Processing, 2021, 20
  • [44] Solving Sudoku game using a hybrid classical-quantum algorithm
    Pal, Ankur
    Chandra, Sanghita
    Mongia, Vardaan
    Behera, Bikash K.
    Panigrahi, Prasanta K.
    EPL, 2019, 128 (04)
  • [45] Domain adaptation based on hybrid classical-quantum neural network
    Yihua Wu
    Chunhui Wu
    Anqi Zhang
    Shengmei Zhao
    Quantum Information Processing, 22
  • [46] The Design and Implementation of a Hybrid Classical-Quantum Annealing Polar Decoder
    Kasi, Srikar
    Kaewell, John
    Jamieson, Kyle
    2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 5819 - 5825
  • [47] Retrieving past quantum features with deep hybrid classical-quantum reservoir computing
    Nokkala, Johannes
    Giorgi, Gian Luca
    Zambrini, Roberta
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2024, 5 (03):
  • [48] Image Classification Using Hybrid Classical-Quantum Neutral Networks
    Ling, Ya-Qi
    Zhang, Jun-Hu
    Zhang, Li-Hua
    Li, Yan-Ran
    Huang, Hui-Lei
    INTERNATIONAL JOURNAL OF THEORETICAL PHYSICS, 2024, 63 (05)
  • [49] An end-to-end trainable hybrid classical-quantum classifier
    Chen, Samuel Yen-Chi
    Huang, Chih-Min
    Hsing, Chia-Wei
    Kao, Ying-Jer
    MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2021, 2 (04):
  • [50] Domain adaptation based on hybrid classical-quantum neural network
    Wu, Yihua
    Wu, Chunhui
    Zhang, Anqi
    Zhao, Shengmei
    QUANTUM INFORMATION PROCESSING, 2023, 22 (06)