Memory-Sample Lower Bounds for Learning with Classical-Quantum Hybrid Memory
Memory-Sample Lower Bounds for Learning with Classical-Quantum Hybrid Memory
复制标题
使用经典量子混合内存进行学习的内存样本下限
DOI:
10.1145/3564246.3585129
复制
发表时间:
2023
期刊:
影响因子:
--
通讯作者:
Zhan, Wei
中科院分区:
文献类型:
--
作者:
Liu, Qipeng;Raz, Ran;Zhan, Wei
In a work by Raz (J. ACM and FOCS 16), it was proved that any algorithm for parity learning onnbits requires either Ω(n2) 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 onnbits, requires either Ω(n2) bits of classical memory or Ω(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 sizecn(for some constantc>0). Our result is more general and applies to many other classical learning tasks. Following previous works, we represent by the matrixM:A×X→ {−1,1} the following learning task. An unknownxis sampled uniformly at random from a concept classX, and a learning algorithm tries to uncoverxby seeing streaming of random samples (ai,bi=M(ai,x)) where for everyi,ai∈Ais chosen uniformly at random. Assume thatk,ℓ,rare integers such that any submatrix ofMof at least 2−k·|A| rows and at least 2−ℓ·|X| 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 toMneeds either (1) Ω(k· ℓ) bits of classical memory, or (2) Ω(r) qubits of quantum memory, or (3) 2Ω(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 onnbits), proving that security holds even in the presence of a quantum adversary with at mostcn2bits of classical memory andcnbits of quantum memory (for some constantc>0).
登录
查看更多内容
DOI:
10.1007/978-3-030-92641-0_14
发表时间:
2021
期刊:
IACR Cryptol. ePrint Arch.
影响因子:
--
作者:
Jiahui Liu;Satyanarayana Vusirikala
通讯作者:
Satyanarayana Vusirikala
DOI:
--
发表时间:
2006
期刊:
International Colloquium on Automata, Languages and Programming
影响因子:
--
作者:
Danny Harnik;M. Naor
通讯作者:
M. Naor
DOI:
10.1007/978-3-031-30545-0_4
发表时间:
2021
期刊:
IACR Cryptol. ePrint Arch.
影响因子:
--
作者:
Y. Dodis;Willy Quach;Daniel Wichs
通讯作者:
Daniel Wichs
DOI:
10.1007/978-3-031-07082-2_26
发表时间:
2022
期刊:
SIAM J. Discret. Math.
影响因子:
--
作者:
Y. Dodis;Willy Quach;Daniel Wichs
通讯作者:
Daniel Wichs
DOI:
10.4230/lipics.itcs.2018.28
发表时间:
2018
期刊:
--
影响因子:
--
作者:
Dana Moshkovitz;Michal Moshkovitz
通讯作者:
Dana Moshkovitz;Michal Moshkovitz