REVIEW 7 cited by
The effect of data encoding on the expressive power of variational quantum machine learning models
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
Quantum computers can be used for supervised learning by treating parametrised quantum circuits as models that map data inputs to predictions. While a lot of work has been done to investigate practical implications of this approach, many important theoretical properties of these models remain unknown. Here we investigate how the strategy with which data is encoded into the model influences the expressive power of parametrised quantum circuits as function approximators. We show that one can naturally write a quantum model as a partial Fourier series in the data, where the accessible frequencies are determined by the nature of the data encoding gates in the circuit. By repeating simple data encoding gates multiple times, quantum models can access increasingly rich frequency spectra. We show that there exist quantum models which can realise all possible sets of Fourier coefficients, and therefore, if the accessible frequency spectrum is asymptotically rich enough, such models are universal function approximators.
Forward citations
Cited by 7 Pith papers
-
High-rate qLDPC processors
Non-abelian "mitten" qLDPC codes achieve 20% encoding rate with distances 10-24 on 150-975 qubits, and simulations indicate fault-tolerant processors sustaining ~10^10 logical operations at 0.1% physical error rate.
-
The Fourier Wall: Why Public Tabular Datasets Refuse Quantum Advantage, and a Certified Recipe for Where It Lives
Quantum models beat tuned classical baselines on tabular data only when the target spectrum is off-grid, high-order, high-frequency, near-independent, and dense; SPECTRA certifies these conditions and refuses most pub...
-
Exploiting biased noise in variational quantum models
Twirling amplitude-damping noise into uniform Pauli/depolarising channels reduces expressivity and gradient magnitudes, while preserving the noise bias yields better VQA optimisation in the studied models.
-
Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning
Classical uncertainty quantification methods transfer to quantum machine learning; Bayesian quantum models and Gaussian dropout give the best-calibrated uncertainty estimates in small simulated experiments.
-
Out of Tune: Demystifying Noise-Effects on Quantum Fourier Models
Noise, especially decoherent gate errors, systematically reduces Fourier coefficient magnitudes, expressibility, and entangling capability of quantum Fourier models, with circuit architecture and encoding modulating t...
-
Quantum Topological Data Encoding
QTDE encodes higher-order topological structure into quantum states via evolution under the combinatorial Laplacian; on clique-complex benchmarks it edges out a Laplacian-comparison baseline only in easy, high-dimensi...
-
Auto Quantum Machine Learning for Multisource Classification
AQML-found quantum circuits match classical MLPs on multisource classification and improve on a previous QML change-detection result (0.743 vs 0.720).
Discussion (0). Sign in to comment.