The use of adversaries for optimal neural network training

Hawthorne-Gonzalvez, Anton; Sevior, M. E.

doi:10.1016/j.nima.2018.10.043

Cited by 4 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An established way to test a network is to exclude known, well-defined pieces of information from it through adversarial networks [51][52][53][54][55][56][57]. They consist of two networks playing against each other.…”

Section: De-correlating the Massmentioning

confidence: 99%

“…In this paper we will go even further and show how autoencoders work in the absence of a signal sample. The second challenge can for example be addressed with adversarial networks, de-correlating for example kinematic information or theory assumptions [50][51][52][53][54][55][56][57]. Alternatively, refiner networks [84] can be used to improve the quality of simulation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

QCD or what?

et al. 2019

View full text Add to dashboard Cite

Autoencoder networks, trained only on QCD jets, can be used to search for anomalies in jet-substructure. We show how, based either on images or on 4-vectors, they identify jets from decays of arbitrary heavy resonances. To control the backgrounds and the underlying systematics we can de-correlate the jet mass using an adversarial network. Such an adversarial autoencoder allows for a general and at the same time easily controllable search for new physics. Ideally, it can be trained and applied to data in the same phase space region, allowing us to efficiently search for new physics using un-supervised learning.

show abstract

Section: De-correlating the Massmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

QCD or what?

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The number of input data sets and performance in the quantum approach was limited due to the size and error rates of current quantum computers. If expanded to use more inputs and larger dataset sizes it is foreseeable that the QSVM may be able to compete with current state-of-the-art classical techniques, which can achieve AUCs of 0.930 [10]. There are a plethora of alternative quantum machine learning methods that could utilise the encoding circuits discussed here.…”

Section: Discussionmentioning

confidence: 99%

“…We refer to these particles as originating from the B candidate. If we use particles from the B candidate itself to perform the classification then we run the risk of sculpting the background to look like signal [10]. We therefore exclude particles associated with the B candidate and use the variables from the other B meson which are not correlated with the kinematic variables of the signal B.…”

Section: Introductionmentioning

confidence: 99%

Quantum Support Vector Machines for Continuum Suppression in B Meson Decays

Heredge

Hill

Hollenberg

et al. 2021

Comput Softw Big Sci

Self Cite

View full text Add to dashboard Cite

Quantum computers have the potential to speed up certain computational tasks. A possibility this opens up within the field of machine learning is the use of quantum techniques that may be inefficient to simulate classically but could provide superior performance in some tasks. Machine learning algorithms are ubiquitous in particle physics and as advances are made in quantum machine learning technology there may be a similar adoption of these quantum techniques. In this work a quantum support vector machine (QSVM) is implemented for signal-background classification. We investigate the effect of different quantum encoding circuits, the process that transforms classical data into a quantum state, on the final classification performance. We show an encoding approach that achieves an average Area Under Receiver Operating Characteristic Curve (AUC) of 0.848 determined using quantum circuit simulations. For this same dataset the best classical method tested, a classical Support Vector Machine (SVM) using the Radial Basis Function (RBF) Kernel achieved an AUC of 0.793. Using a reduced version of the dataset we then ran the algorithm on the IBM Quantum ibmq_casablanca device achieving an average AUC of 0.703. As further improvements to the error rates and availability of quantum computers materialise, they could form a new approach for data analysis in high energy physics.

show abstract

“…The amount of inputs in our approach was limited due to the size and error rates of current quantum computers. If expanded to use all the available data, it is foreseeable that the QSVM may be able to compete with current state-of-the-art classical techniques, which can achieve AUCs of 0.930 [27]. There are also a plethora of alternatives to using an SVM method; quantum generated features created from the encoding gates explored here could be passed to another classical or quantum classifying algorithm.…”

Section: Discussionmentioning

confidence: 99%

Quantum Support Vector Machines for Continuum Suppression in B Meson Decays

Heredge¹,

Hill²,

Hollenberg³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Quantum computers have the potential for significant speed-ups of certain computational tasks. A possibility this opens up within the field of machine learning is the use of quantum features that would be inefficient to calculate classically. Machine learning algorithms are ubiquitous in particle physics and as advances are made in quantum machine learning technology, there may be a similar adoption of these quantum techniques. In this work a quantum support vector machine (QSVM) is implemented for signal-background classification. We investigate the effect of different quantum encoding circuits, the process that transforms classical data into a quantum state, on the final classification performance. We show an encoding approach that achieves an Area Under Receiver Operating Characteristic Curve (AUC) of 0.877 determined using quantum circuit simulations. For this same dataset the best classical method, a classical Support Vector Machine (SVM) using the Radial Basis Function (RBF) Kernel achieved an AUC of 0.865. Using a reduced dataset we then ran the algorithm on the IBM Quantum ibmq_casablanca device achieving an average AUC of 0.703. As further improvements to the error rates and availability of quantum computers materialise, they could form a new approach for data analysis in high energy physics.

show abstract

The use of adversaries for optimal neural network training

Cited by 4 publications

References 17 publications

QCD or what?

QCD or what?

Quantum Support Vector Machines for Continuum Suppression in B Meson Decays

Quantum Support Vector Machines for Continuum Suppression in B Meson Decays

Contact Info

Product

Resources

About