Exponential separations between learning with and without quantum memory

by   Sitan Chen, et al.

We study the power of quantum memory for learning properties of quantum systems and dynamics, which is of great importance in physics and chemistry. Many state-of-the-art learning algorithms require access to an additional external quantum memory. While such a quantum memory is not required a priori, in many cases, algorithms that do not utilize quantum memory require much more data than those which do. We show that this trade-off is inherent in a wide range of learning problems. Our results include the following: (1) We show that to perform shadow tomography on an n-qubit state rho with M observables, any algorithm without quantum memory requires Ω(min(M, 2^n)) samples of rho in the worst case. Up to logarithmic factors, this matches the upper bound of [HKP20] and completely resolves an open question in [Aar18, AR19]. (2) We establish exponential separations between algorithms with and without quantum memory for purity testing, distinguishing scrambling and depolarizing evolutions, as well as uncovering symmetry in physical dynamics. Our separations improve and generalize prior work of [ACQ21] by allowing for a broader class of algorithms without quantum memory. (3) We give the first tradeoff between quantum memory and sample complexity. We prove that to estimate absolute values of all n-qubit Pauli observables, algorithms with k < n qubits of quantum memory require at least Ω(2^(n-k)/3) samples, but there is an algorithm using n-qubit quantum memory which only requires O(n) samples. The separations we show are sufficiently large and could already be evident, for instance, with tens of qubits. This provides a concrete path towards demonstrating real-world advantage for learning algorithms with quantum memory.



There are no comments yet.


page 1

page 2

page 3

page 4


Revisiting dequantization and quantum advantage in learning tasks

It has been shown that the apparent advantage of some quantum machine le...

Fast quantum learning with statistical guarantees

Within the framework of statistical learning theory it is possible to bo...

Quantum versus Classical Online Algorithms with Advice and Logarithmic Space

In this paper, we consider online algorithms. Typically the model is inv...

A note on state preparation for quantum machine learning

The intersection between the fields of machine learning and quantum info...

Quantum advantage in learning from experiments

Quantum technology has the potential to revolutionize how we acquire and...

Control dynamics using quantum memory

We propose a new quantum numerical scheme to control the dynamics of a q...

Efficient Construction of Functional Representations for Quantum Algorithms

Due to the significant progress made in the implementation of quantum ha...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.