Universal replication of chaotic characteristics by classical and quantum machine learning
- URL: http://arxiv.org/abs/2405.08484v1
- Date: Tue, 14 May 2024 10:12:47 GMT
- Title: Universal replication of chaotic characteristics by classical and quantum machine learning
- Authors: Sheng-Chen Bai, Shi-Ju Ran,
- Abstract summary: We show that variational quantum circuit can reproduce the long-term characteristics with higher accuracy than the long short-term memory.
Our results suggest that quantum circuit model exhibits potential advantages on mitigating over-fitting, achieving higher accuracy and stability.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Replicating chaotic characteristics of non-linear dynamics by machine learning (ML) has recently drawn wide attentions. In this work, we propose that a ML model, trained to predict the state one-step-ahead from several latest historic states, can accurately replicate the bifurcation diagram and the Lyapunov exponents of discrete dynamic systems. The characteristics for different values of the hyper-parameters are captured universally by a single ML model, while the previous works considered training the ML model independently by fixing the hyper-parameters to be specific values. Our benchmarks on the one- and two-dimensional Logistic maps show that variational quantum circuit can reproduce the long-term characteristics with higher accuracy than the long short-term memory (a well-recognized classical ML model). Our work reveals an essential difference between the ML for the chaotic characteristics and that for standard tasks, from the perspective of the relation between performance and model complexity. Our results suggest that quantum circuit model exhibits potential advantages on mitigating over-fitting, achieving higher accuracy and stability.
Related papers
- 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) - Scaling and renormalization in high-dimensional regression [72.59731158970894]
This paper presents a succinct derivation of the training and generalization performance of a variety of high-dimensional ridge regression models.
We provide an introduction and review of recent results on these topics, aimed at readers with backgrounds in physics and deep learning.
arXiv Detail & Related papers (2024-05-01T15:59:00Z) - First-Order Phase Transition of the Schwinger Model with a Quantum Computer [0.0]
We explore the first-order phase transition in the lattice Schwinger model in the presence of a topological $theta$-term.
We show that the electric field density and particle number, observables which reveal the phase structure of the model, can be reliably obtained from the quantum hardware.
arXiv Detail & Related papers (2023-12-20T08:27:49Z) - Classical-to-Quantum Transfer Learning Facilitates Machine Learning with Variational Quantum Circuit [62.55763504085508]
We prove that a classical-to-quantum transfer learning architecture using a Variational Quantum Circuit (VQC) improves the representation and generalization (estimation error) capabilities of the VQC model.
We show that the architecture of classical-to-quantum transfer learning leverages pre-trained classical generative AI models, making it easier to find the optimal parameters for the VQC in the training stage.
arXiv Detail & Related papers (2023-05-18T03:08:18Z) - A Novel Stochastic LSTM Model Inspired by Quantum Machine Learning [0.0]
Works in quantum machine learning (QML) over the past few years indicate that QML algorithms can function just as well as their classical counterparts.
This work aims to elucidate if it is possible to achieve some of QML's major reported benefits on classical machines by incorporating itsity.
arXiv Detail & Related papers (2023-05-17T13:44:25Z) - Capturing dynamical correlations using implicit neural representations [85.66456606776552]
We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data.
In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
arXiv Detail & Related papers (2023-04-08T07:55:36Z) - Direct parameter estimations from machine-learning enhanced quantum
state tomography [3.459382629188014]
Machine-learning enhanced quantum state tomography (QST) has demonstrated its advantages in extracting complete information about the quantum states.
We develop a high-performance, lightweight, and easy-to-install supervised characteristic model by generating the target parameters directly.
Such a characteristic model-based ML-QST can avoid the problem of dealing with large Hilbert space, but keep feature extractions with high precision.
arXiv Detail & Related papers (2022-03-30T15:16:02Z) - SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred
from Vision [73.26414295633846]
A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations.
Existing methods rely on image reconstruction quality, which does not always reflect the quality of the learnt latent dynamics.
We develop a set of new measures, including a binary indicator of whether the underlying Hamiltonian dynamics have been faithfully captured.
arXiv Detail & Related papers (2021-11-10T23:26:58Z) - 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) - Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
empirical optimization is central to modern machine learning, but its role in its success is still unclear.
We show that it commonly arises in parameters of discrete multiplicative noise due to variance.
A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
arXiv Detail & Related papers (2020-06-11T09:58:01Z)
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.