The effect of the processing and measurement operators on the expressive power of quantum models

• URL: http://arxiv.org/abs/2211.03101v1
• Date: Sun, 6 Nov 2022 12:57:38 GMT
• Title: The effect of the processing and measurement operators on the expressive power of quantum models
• Authors: Aikaterini (Katerina) Gratsea and Patrick Huembeli
• Abstract summary: We focus 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. This work sketches the role that the processing and measurement operators have on the expressive power of simple quantum circuits.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 ans\"atze 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.

Related papers

• Quantum feature encoding optimization [1.4962440253906657]
  We tackle a largely unaddressed aspect of encoding that is unique to QML modeling.<n>We evaluate if these aspects of encoding can have a significant impact on QML model performance.<n>We show that by optimizing how features are encoded in ansatz we can substantially and consistently improve the performance of QML models.
  arXiv  Detail & Related papers  (2025-12-02T05:07:32Z)
• Evaluating Angle and Amplitude Encoding Strategies for Variational Quantum Machine Learning: their impact on model's accuracy [0.6553587309274792]
  Variational Quantum Circuit (VQC) is a hybrid model where the quantum circuit handles data inference while classical optimization adjusts the parameters of the circuit.<n>This work involves performing an analysis by considering both Amplitude- and Angle-encoding models, and examining how the type of rotational gate applied affects the classification performance of the model.<n>The study demonstrates that, under identical model topologies, the difference in accuracy between the best and worst models ranges from 10% to 30%, with differences reaching up to 41%.
  arXiv  Detail & Related papers  (2025-08-01T16:43:45Z)
• An Efficient Quantum Classifier Based on Hamiltonian Representations [50.467930253994155]
  Quantum machine learning (QML) is a discipline that seeks to transfer the advantages of quantum computing to data-driven tasks. We propose an efficient approach that circumvents the costs associated with data encoding by mapping inputs to a finite set of Pauli strings. We evaluate our approach on text and image classification tasks, against well-established classical and quantum models.
  arXiv  Detail & Related papers  (2025-04-13T11:49:53Z)
• RSQ: Learning from Important Tokens Leads to Better Quantized LLMs [65.5558181902098]
  Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining. We propose RSQ (Rotate, Scale, then Quantize), which applies rotations to the model to mitigate outliers. We demonstrate that RSQ consistently outperforms baseline methods across multiple downstream tasks and three model families.
  arXiv  Detail & Related papers  (2025-03-03T18:46:33Z)
• Quantum Machine Learning in Log-based Anomaly Detection: Challenges and Opportunities [36.437593835024394]
  We introduce a unified framework, ourframework, for evaluating QML models in the context of LogAD. State-of-the-art methods such as DeepLog, LogAnomaly, and LogRobust are included in our framework. Our evaluation extends to factors critical to QML performance, such as specificity, the number of circuits, circuit design, and quantum state encoding.
  arXiv  Detail & Related papers  (2024-12-18T06:13:49Z)
• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• On the relation between trainability and dequantization of variational quantum learning models [1.7999333451993955]
  We study the relation between trainability and dequantization of variational quantum machine learning (QML) We introduce recipes for building PQC-based QML models which are both trainable and nondequantizable. Our work however does point toward a way forward for finding more general constructions, for which finding applications may become feasible.
  arXiv  Detail & Related papers  (2024-06-11T08:59:20Z)
• A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation Analysis [128.0532113800092]
  We present a mechanistic interpretation of Transformer-based LMs on arithmetic questions. This provides insights into how information related to arithmetic is processed by LMs.
  arXiv  Detail & Related papers  (2023-05-24T11:43:47Z)
• Reflection Equivariant Quantum Neural Networks for Enhanced Image Classification [0.7232471205719458]
  We build new machine learning models which explicitly respect the symmetries inherent in their data, so-called geometric quantum machine learning (GQML) We find that these networks are capable of consistently and significantly outperforming generic ansatze on complicated real-world image datasets.
  arXiv  Detail & Related papers  (2022-12-01T04:10:26Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Equivariant quantum circuits for learning on weighted graphs [0.0]
  We introduce an ansatz for learning tasks on weighted graphs. We evaluate the performance of this ansatz on a complex learning task, namely neural optimization.
  arXiv  Detail & Related papers  (2022-05-12T14:15:47Z)
• Study of Feature Importance for Quantum Machine Learning Models [0.0]
  Predictor importance is a crucial part of data preprocessing pipelines in classical and quantum machine learning (QML) This work presents the first study of its kind in which feature importance for QML models has been explored and contrasted against their classical machine learning (CML) equivalents. We developed a hybrid quantum-classical architecture where QML models are trained and feature importance values are calculated from classical algorithms on a real-world dataset.
  arXiv  Detail & Related papers  (2022-02-18T15:21:47Z)
• Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data [66.11139091362078]
  We provide the first model selection results on large pretrained Transformers from Huggingface using generalization metrics. Despite their niche status, we find that metrics derived from the heavy-tail (HT) perspective are particularly useful in NLP tasks.
  arXiv  Detail & Related papers  (2022-02-06T20:07:35Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• Quantum-tailored machine-learning characterization of a superconducting qubit [50.591267188664666]
  We develop an approach to characterize the dynamics of a quantum device and learn device parameters. This approach outperforms physics-agnostic recurrent neural networks trained on numerically generated and experimental data. This demonstration shows how leveraging domain knowledge improves the accuracy and efficiency of this characterization task.
  arXiv  Detail & Related papers  (2021-06-24T15:58:57Z)
• Structural risk minimization for quantum linear classifiers [0.0]
  Quantum machine learning (QML) stands out as one of the typically highlighted candidates for quantum computing's near-term "killer application" We investigate capacity measures of two closely related QML models called explicit and implicit quantum linear classifiers. We identify that the rank and Frobenius norm of the observables used in the QML model closely control the model's capacity.
  arXiv  Detail & Related papers  (2021-05-12T10:39:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.