REVIEW 7 cited by
Exponential separations between classical and quantum learners
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Despite significant effort, the quantum machine learning community has only demonstrated quantum learning advantages for artificial cryptography-inspired datasets when dealing with classical data. In this paper we address the challenge of finding learning problems where quantum learning algorithms can achieve a provable exponential speedup over classical learning algorithms. We reflect on computational learning theory concepts related to this question and discuss how subtle differences in definitions can result in significantly different requirements and tasks for the learner to meet and solve. We examine existing learning problems with provable quantum speedups and find that they largely rely on the classical hardness of evaluating the function that generates the data, rather than identifying it. To address this, we present two new learning separations where the classical difficulty primarily lies in identifying the function generating the data. Furthermore, we explore computational hardness assumptions that can be leveraged to prove quantum speedups in scenarios where data is quantum-generated, which implies likely quantum advantages in a plethora of more natural settings (e.g., in condensed matter and high energy physics). We also discuss the limitations of the classical shadow paradigm in the context of learning separations, and how physically-motivated settings such as characterizing phases of matter and Hamiltonian learning fit in the computational learning framework.
Forward citations
Cited by 7 Pith papers
-
Provable learning separation for predicting time-evolution of quantum many-body systems
A provable exponential quantum-classical learning separation is established for predicting expectation values of time-evolved quantum states under unknown low-intersection Hamiltonians, assuming BQP ⊄ P/poly.
-
The role of data-induced randomness in quantum machine learning classification tasks
Introduces a class-margin metric connecting data-encoding randomness to quantum classification accuracy, and argues that near-random encodings fundamentally limit performance.
-
Addressing the Readout Problem in Quantum Differential Equation Algorithms with Quantum Scientific Machine Learning
Quantum neural networks can classify shock and turbulent flow solutions encoded as quantum states, with accuracy strongly dependent on Fourier versus real-space basis choice.
-
Quantum Active Learning for Structural Determination of Doped Nanoparticles -- a Case Study of 4Al@Si$_{11}$
A quantum active learning workflow using quantum Gaussian process regression with projected and fidelity quantum kernels finds the global minimum of 4Al@Si11, but with no clear advantage over classical active learning...
-
Quantum computing and artificial intelligence: status and perspectives
A broad expert white paper sets a European research agenda for combining quantum computing and AI, spanning quantum machine learning, AI-driven quantum control, and foundational questions.
-
Hybrid Quantum Neural Networks: Theory, Implementations, and Applications
A balanced review of hybrid quantum neural networks, concluding that quantum layers help on structured, small-scale and quantum-native problems but do not yet beat classical models on generic benchmarks.
-
Artificial intelligence for representing and characterizing quantum systems
A review organizes AI-based quantum system characterization into ML, deep learning, and language model paradigms, covering property prediction and implicit state reconstruction.
Discussion (0). Continue with ORCID to comment.