Generalization with data-dependent quantum geometry
- URL: http://arxiv.org/abs/2303.13462v2
- Date: Mon, 13 May 2024 13:04:32 GMT
- Title: Generalization with data-dependent quantum geometry
- Authors: Tobias Haug, M. S. Kim,
- Abstract summary: We introduce the data quantum Fisher information metric (DQFIM)
It describes the capacity of variational quantum algorithms depending on variational ansatz, training data and their symmetries.
Using the Lie algebra, we explain how to generalize using a low number of training states.
Finally, we find that out-of-distribution generalization, where training and testing data are drawn from different data distributions, can be better than using the same distribution.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Generalization is the ability of machine learning models to make accurate predictions on new data by learning from training data. However, understanding generalization of quantum machine learning models has been a major challenge. Here, we introduce the data quantum Fisher information metric (DQFIM). It describes the capacity of variational quantum algorithms depending on variational ansatz, training data and their symmetries. We apply the DQFIM to quantify circuit parameters and training data needed to successfully train and generalize. Using the dynamical Lie algebra, we explain how to generalize using a low number of training states. Counter-intuitively, breaking symmetries of the training data can help to improve generalization. Finally, we find that out-of-distribution generalization, where training and testing data are drawn from different data distributions, can be better than using the same distribution. Our work provides a useful framework to explore the power of quantum machine learning models.
Related papers
- 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) - $\zeta$-QVAE: A Quantum Variational Autoencoder utilizing Regularized
Mixed-state Latent Representations [1.1674893622721483]
A major challenge in near-term quantum computing is its application to large real-world datasets due to scarce quantum hardware resources.
We present a fully quantum framework, $zeta$-QVAE, which encompasses all the capabilities of classical VAEs.
Our results consistently indicate that $zeta$-QVAE exhibits similar or better performance compared to matched classical models.
arXiv Detail & Related papers (2024-02-27T18:37:01Z) - Understanding quantum machine learning also requires rethinking
generalization [0.3683202928838613]
We show that traditional approaches to understanding generalization fail to explain the behavior of quantum models.
Experiments reveal that state-of-the-art quantum neural networks accurately fit random states and random labeling of training data.
arXiv Detail & Related papers (2023-06-23T12:04:13Z) - 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) - Automatic Data Augmentation via Invariance-Constrained Learning [94.27081585149836]
Underlying data structures are often exploited to improve the solution of learning tasks.
Data augmentation induces these symmetries during training by applying multiple transformations to the input data.
This work tackles these issues by automatically adapting the data augmentation while solving the learning task.
arXiv Detail & Related papers (2022-09-29T18:11:01Z) - Do Quantum Circuit Born Machines Generalize? [58.720142291102135]
We present the first work in the literature that presents the QCBM's generalization performance as an integral evaluation metric for quantum generative models.
We show that the QCBM is able to effectively learn the reweighted dataset and generate unseen samples with higher quality than those in the training set.
arXiv Detail & Related papers (2022-07-27T17:06:34Z) - Out-of-distribution generalization for learning quantum dynamics [2.1503874224655997]
We show that one can learn the action of a unitary on entangled states having trained only product states.
This advances the prospects of learning quantum dynamics on near term quantum hardware.
arXiv Detail & Related papers (2022-04-21T17:15:23Z) - Generalization in quantum machine learning from few training data [4.325561431427748]
Modern quantum machine learning (QML) methods involve variationally optimizing a parameterized quantum circuit on a training data set.
We show that the generalization error of a quantum machine learning model with $T$ trainable gates at worst as $sqrtT/N$.
We also show that classification of quantum states across a phase transition with a quantum convolutional neural network requires only a very small training data set.
arXiv Detail & Related papers (2021-11-09T17:49:46Z) - Out-of-Distribution Generalization in Kernel Regression [21.958028127426196]
We study generalization in kernel regression when the training and test distributions are different.
We identify an overlap matrix that quantifies the mismatch between distributions for a given kernel.
We develop procedures for optimizing training and test distributions for a given data budget to find best and worst case generalizations under the shift.
arXiv Detail & Related papers (2021-06-04T04:54:25Z) - Post-mortem on a deep learning contest: a Simpson's paradox and the
complementary roles of scale metrics versus shape metrics [61.49826776409194]
We analyze a corpus of models made publicly-available for a contest to predict the generalization accuracy of neural network (NN) models.
We identify what amounts to a Simpson's paradox: where "scale" metrics perform well overall but perform poorly on sub partitions of the data.
We present two novel shape metrics, one data-independent, and the other data-dependent, which can predict trends in the test accuracy of a series of NNs.
arXiv Detail & Related papers (2021-06-01T19:19:49Z) - Unshuffling Data for Improved Generalization [65.57124325257409]
Generalization beyond the training distribution is a core challenge in machine learning.
We show that partitioning the data into well-chosen, non-i.i.d. subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
arXiv Detail & Related papers (2020-02-27T03:07:41Z)
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.