Revisiting dequantization and quantum advantage in learning tasks

Abstract

It has been shown that the apparent advantage of some quantum machine learning algorithms may be efficiently replicated using classical algorithms with suitable data access -- a process known as dequantization. Existing works on dequantization compare quantum algorithms which take copies of an n-qubit quantum state $|x⟩={\sum }_i{x}_i|i⟩$ as input to classical algorithms which have sample and query (SQ) access to the vector $x$. In this note, we prove that classical algorithms with SQ access can accomplish some learning tasks exponentially faster than quantum algorithms with quantum state inputs. Because classical algorithms are a subset of quantum algorithms, this demonstrates that SQ access can sometimes be significantly more powerful than quantum state inputs. Our findings suggest that the absence of exponential quantum advantage in some learning tasks may be due to SQ access being too powerful relative to quantum state inputs. If we compare quantum algorithms with quantum state inputs to classical algorithms with access to measurement data on quantum states, the landscape of quantum advantage can be dramatically different. We remark that when the quantum states are constructed from exponential-size classical data, comparing SQ access and quantum state inputs is appropriate since both require exponential time to prepare.

arXiv comment6 pages, 1 figure; v2: further exposition added

References in corpus (9)

• Quantum Machine Learning
• Quantum algorithm for solving linear systems of equations
• Quantum support vector machine for big data classification
• Quantum principal component analysis
• Quantum advantage in learning from experiments
• Sampling-based sublinear low-rank matrix arithmetic framework for dequantizing quantum machine learning
• Quantum Algorithmic Measurement
• The Church of the Symmetric Subspace
• Quantum-inspired low-rank stochastic regression with logarithmic dependence on the dimension

Cited by in corpus (1)

• Accelerating Quantum Algorithms with Precomputation