Machine Learning in a Quantum World

Aïmeur, Esma; Brassard, Gilles; Gambs, Sébastien

doi:10.1007/11766247_37

Cited by 126 publications

(106 citation statements)

References 15 publications

Supporting

Mentioning

106

Contrasting

Order By: Relevance

“…In this section, we detail a model and tools that can be used to quantize unsupervised learning algorithms, among which specifically clustering algorithms. Although related, the task of quantizing a clustering algorithm should not be confused with the design of classical algorithms inspired from quantum mechanics Gottlieb 2001, 2002) or the task of performing clustering directly on quantum information (Aïmeur et al 2006). …”

Section: Quantization Of Clustering Algorithmsmentioning

confidence: 99%

Quantum speed-up for unsupervised learning

2012

Self Cite

View full text Add to dashboard Cite

We show how the quantum paradigm can be used to speed up unsupervised learning algorithms. More precisely, we explain how it is possible to accelerate learning algorithms by quantizing some of their subroutines. Quantization refers to the process that partially or totally converts a classical algorithm to its quantum counterpart in order to improve performance. In particular, we give quantized versions of clustering via minimum spanning tree, divisive clustering and k-medians that are faster than their classical analogues. We also describe a distributed version of k-medians that allows the participants to save on the global communication cost of the protocol compared to the classical version. Finally, we design quantum algorithms for the construction of a neighbourhood graph, outlier detection as well as smart initialization of the cluster centres.

show abstract

Section: Quantization Of Clustering Algorithmsmentioning

confidence: 99%

Quantum speed-up for unsupervised learning

2012

Self Cite

View full text Add to dashboard Cite

show abstract

“…By assumption, the adversary demands that F e o R Î -( ) which is inconsistent with the bound in (25). Therefore we must have that Q o N d Î ( )and our result holds regardless of the value of Q. ,…”

Section: Thus the Probability Of Success Obeysmentioning

confidence: 74%

“…Quantum computing has experienced a similar surge of interest of late and this had led to a synergistic relationship wherein quantum computers have been found to have profound implications for machine learning [24][25][26][27][28][29][30][31][32][33][34][35][36][37] and machine learning has been shown to be invaluable for characterizing, controlling and error correcting such quantum computers [38][39][40]. However, as of late the question of what quantum computers can do to protect machine learning from adversaries is relatively underdeveloped.…”

Section: Introductionmentioning

confidence: 99%

Hardening quantum machine learning against adversaries

Wiebe

Kumar

2018

New J. Phys.

View full text Add to dashboard Cite

Security of machine learning has begun to become a serious issue for present day applications. An important question remaining is whether emerging quantum technologies will help or hinder the security of machine learning. Here we discuss a number of ways that quantum information can be used to help make quantum classifiers more secure or private. In particular, we demonstrate a form of robust principal component analysis that, under some circumstances, can provide an exponential speedup relative to robust methods used at present. To demonstrate this approach we introduce a linear combinations of unitaries Hamiltonian simulation method that we show functions when given an imprecise Hamiltonian oracle, which may be of independent interest. We also introduce a new quantum approach for bagging and boosting that can use quantum superposition over the classifiers or splits of the training set to aggragate over many more models than would be possible classically. Finally, we provide a private form of k-means clustering that can be used to prevent an all powerful adversary from learning more than a small fraction of a bit from any user. These examples show the role that quantum technologies can play in the security of ML and vice versa. This illustrates that quantum computing can provide useful advantages to machine learning apart from speedups.

show abstract

“…Although related, the task of quantizing clustering algorithms should not be confused with the design of classical clustering algorithms inspired from quantum mechanics (Horn and Gottlieb 2001; or the task of performing clustering directly on quantum states (Aïmeur, Brassard & Gambs, 2006).…”

Section: Quantization Of Clustering Algorithmsmentioning

confidence: 99%

Quantum clustering algorithms

Aïmeur

Brassard

Gambs

2007

Proceedings of the 24th International Conference on Machine Learning

Self Cite

View full text Add to dashboard Cite

By the term "quantization", we refer to the process of using quantum mechanics in order to improve a classical algorithm, usually by making it go faster. In this paper, we initiate the idea of quantizing clustering algorithms by using variations on a celebrated quantum algorithm due to Grover. After having introduced this novel approach to unsupervised learning, we illustrate it with a quantized version of three standard algorithms: divisive clustering, k-medians and an algorithm for the construction of a neighbourhood graph. We obtain a significant speedup compared to the classical approach.

show abstract

Machine Learning in a Quantum World

Cited by 126 publications

References 15 publications

Quantum speed-up for unsupervised learning

Quantum speed-up for unsupervised learning

Hardening quantum machine learning against adversaries

Quantum clustering algorithms

Contact Info

Product

Resources

About