There is an increasing interest in Quantum Machine Learning (QML) models, how they work and for which applications they could be useful. There have been many different proposals on how classical data can be encoded and what circuit ansätze and measurement operators should be used to process the encoded data and measure the output state of an ansatz. The choice of the aforementioned operators plays a determinant role in the expressive power of the QML model. In this work we investigate how certain changes in the circuit structure change this expressivity. We introduce both numerical and analytical tools to explore the effect that these operators have in the overall performance of the QML model. These tools are based on previous work on the teacher-student scheme, the partial Fourier series and the averaged operator size. We focus our analysis on simple QML models with two and three qubits and observe that increasing the number of parameterized and entangling gates leads to a more expressive model for certain circuit structures. Also, on which qubit the measurement is performed affects the type of functions that QML models could learn. This work sketches the determinant role that the processing and measurement operators have on the expressive power of simple quantum circuits.
There is an increasing interest in Quantum Machine Learning (QML) models, how they work and for which applications they could be useful. There have been many different proposals on how classical data can be encoded and what circuit ansätze and measurement operators should be used to process the encoded data and measure the output state of an ansatz. The choice of the aforementioned operators plays a determinant role in the expressive power of the QML model. In this work we investigate how certain changes in the circuit structure change this expressivity. We introduce both numerical and analytical tools to explore the effect that these operators have in the overall performance of the QML model. These tools are based on previous work on the teacher-student scheme, the partial Fourier series and the averaged operator size. We focus our analysis on simple QML models with two and three qubits and observe that increasing the number of parameterized and entangling gates leads to a more expressive model for certain circuit structures. Also, on which qubit the measurement is performed affects the type of functions that QML models could learn. This work sketches the determinant role that the processing and measurement operators have on the expressive power of simple quantum circuits.
Quantum computers can be used for supervised learning by treating parametrized quantum circuits as models that map data inputs to predictions. While a lot of work has been done to investigate the practical implications of this approach, many important theoretical properties of these models remain unknown. Here, we investigate how the strategy with which data are encoded into the model influences the expressive power of parametrized 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 realize all possible sets of Fourier coefficients, and therefore, if the accessible frequency spectrum is asymptotically rich enough, such models are universal function approximators.
Quantum Machine Learning (QML) holds the promise of enhancing machine learning modeling in terms of both complexity and accuracy. A key challenge in this domain is the encoding of input data, which plays a pivotal role in determining the performance of QML models. In this work, we tackle a largely unaddressed aspect of encoding that is unique to QML modeling -- rather than adjusting the ansatz used for encoding, we consider adjusting how data is conveyed to the ansatz. We specifically implement QML pipelines that leverage classical data manipulation (i.e., ordering, selecting, and weighting features) as a preprocessing step, and evaluate if these aspects of encoding can have a significant impact on QML model performance, and if they can be effectively optimized to improve performance. Our experimental results, applied across a wide variety of data sets, ansatz, and circuit sizes, with a representative QML approach, demonstrate that by optimizing how features are encoded in an ansatz we can substantially and consistently improve the performance of QML models, making a compelling case for integrating these techniques in future QML applications. Finally we demonstrate the practical feasibility of this approach by running it using real quantum hardware with 100 qubit circuits and successfully achieving improved QML modeling performance in this case as well.
Expressibility is a crucial factor of a Parameterized Quantum Circuit (PQC). In the context of Variational Quantum Algorithms (VQA) based Quantum Machine Learning (QML), a QML model composed of highly expressible PQC and sufficient number of qubits is theoretically capable of approximating any arbitrary continuous function. While much research has explored the relationship between expressibility and learning performance, as well as the number of layers in PQCs, the connection between expressibility and PQC structure has received comparatively less attention. In this paper, we analyze the connection between expressibility and the types of quantum gates within PQCs using a Gradient Boosting Tree model and SHapley Additive exPlanations (SHAP) values. Our analysis is performed on 1,615 instances of PQC derived from 19 PQC topologies, each with 2-18 qubits and 1-5 layers. The findings of our analysis provide guidance for designing highly expressible PQCs, suggesting the integration of more RX or RY gates while maintaining a careful balance with the number of CNOT gates. Furthermore, our evaluation offers an additional evidence of expressibility saturation, as observed by previous studies.
Quantum neural networks (QNNs), represented by parameterized quantum circuits, can be trained in the paradigm of supervised learning to map input data to predictions. Much work has focused on theoretically analyzing the expressive power of QNNs. However, in almost all literature, QNNs' expressive power is numerically validated using only simple univariate functions. We surprisingly discover that state-of-the-art QNNs with strong expressive power can have poor performance in approximating even just a simple sinusoidal function. To fill the gap, we propose four expressibility-enhancing strategies for QNNs: Sinusoidal-friendly embedding, redundant measurement, post-measurement function, and random training data. We analyze the effectiveness of these strategies via mathematical analysis and/or numerical studies including learning complex sinusoidal-based functions. Our results from comparative experiments validate that the four strategies can significantly increase the QNNs' performance in approximating complex multivariable functions and reduce the quantum circuit depth and qubits required.
Quantum Neural Networks (QNN) and Quantum Long Short-Term Memory (QLSTM) models are emerging as powerful tools in quantum machine learning. The effectiveness of these models is largely governed by the structure of their parameterized quantum circuits, also known as Ansätze. The Expressibility (measure of how well an ansätz can explore Hilbert space), Entanglement (which governs the correlation between states of multiple qubits), and Depth (a measure of how many layers of quantum gates a circuit has) are fundamental to a model’s capacity to learn complex patterns. In this paper, we analyze how varying these attributes for various ansätze influences classification cost and accuracy. We evaluated QNN and QLSTM models across three cybersecurity datasets using ten ansätze with varying expressibility and complexity. Results showed that ansätze with lower expressibility and complexity achieved accuracy and training stability comparable to the more complex ones. Additionally, we found that QNN models consistently offered a better trade-off between accuracy, training time, and computational efficiency compared to QLSTM models.
Using Hamiltonian encoding to inject an input into parameterized quantum circuits (PQCs), the output of the PQC can be written as truncated Fourier series. In recent years, the expressivity of PQCs was established as the number of frequencies contained in this Fourier series. While this concept has also been applied to other quantum machine learning (QML) paradigms, a clear notion of expressivity for temporal information processing with quantum systems is still lacking. Here, we introduce such a notion to the field of quantum reservoir computing (QRC). We analytically derive an expression for the readouts showing that the output of a QRC can be interpreted as a multi-dimensional Fourier series. We give a formula for the growth of expressivity induced by the sequential information injection, which we corroborate with numerical simulations, calculating explicitly the number of multi-dimensional output functions which can be generated from the readouts. Our results show that the specific interplay between system size, input encoding, and memory time gives rise to a boundary on the system size beyond which it is obstructive to further increase the reservoir size in extreme scrambling systems. We propose a recipe for determining this maximal system size for a given QRC setup.