Quantum speed-up for unsupervised learning

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.

[1]  G. Brassard,et al.  Quantum Amplitude Amplification and Estimation , 2000, quant-ph/0005055.

[2]  Eibe Frank,et al.  An Empirical Comparison of Exact Nearest Neighbour Algorithms , 2007, PKDD.

[3]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[4]  Julia Kempe,et al.  Quantum random walks: An introductory overview , 2003, quant-ph/0303081.

[5]  David Harel,et al.  On Clustering Using Random Walks , 2001, FSTTCS.

[6]  R. Cleve,et al.  ar X iv : 0 90 7 . 35 84 v 1 [ qu an t-ph ] 2 1 Ju l 2 00 9 Non-locality and Communication Complexity , 2009 .

[7]  Graham J. Williams,et al.  On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms , 2000, KDD '00.

[8]  G. Brassard,et al.  Quantum Communication Complexity , 2003 .

[9]  Charles T. Zahn,et al.  Graph-Theoretical Methods for Detecting and Describing Gestalt Clusters , 1971, IEEE Transactions on Computers.

[10]  Elham Kashefi,et al.  Parallelizing quantum circuits , 2007, Theor. Comput. Sci..

[11]  Mehdi Mhalla,et al.  Quantum Query Complexity of Some Graph Problems , 2004, SIAM J. Comput..

[12]  Charles H. Bennett,et al.  Communication via one- and two-particle operators on Einstein-Podolsky-Rosen states. , 1992, Physical review letters.

[13]  Peter J. Rousseeuw,et al.  Clustering by means of medoids , 1987 .

[14]  Ian Witten,et al.  Data Mining , 2000 .

[15]  R. Prim.  Shortest connection networks and some generalizations , 1957 .

[16]  M. Sipser,et al.  Quantum Computation by Adiabatic Evolution , 2000, quant-ph/0001106.

[17]  Michael C. Hout,et al.  Multidimensional Scaling , 2003, Encyclopedic Dictionary of Archaeology.

[18]  J. Gower,et al.  Minimum Spanning Trees and Single Linkage Cluster Analysis , 1969 .

[19]  I. Chuang,et al.  Quantum Computation and Quantum Information: Introduction to the Tenth Anniversary Edition , 2010 .

[20]  S. P. Lloyd,et al.  Least squares quantization in PCM , 1982, IEEE Trans. Inf. Theory.

[21]  P. Rousseeuw,et al.  Least median of squares: a robust method for outlier and model error detection in regression and calibration , 1986 .

[22]  Gilles Brassard,et al.  An optimal quantum algorithm to approximate the mean and its application for approximating the median of a set of points over an arbitrary distance , 2011, ArXiv.

[23]  Lov K. Grover.  Quantum Mechanics Helps in Searching for a Needle in a Haystack , 1997, quant-ph/9706033.

[24]  Christoph Dürr,et al.  A Quantum Algorithm for Finding the Minimum , 1996, ArXiv.

[25]  E. Kushilevitz,et al.  Communication Complexity: Basics , 1996 .

[26]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[27]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[28]  Zonghai Chen,et al.  Quantum Reinforcement Learning , 2005, ICNC.

[29]  Felix Wu,et al.  The quantum query complexity of approximating the median and related statistics , 1998, STOC '99.

[30]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[31]  Peter W. Shor,et al.  Polynomial-Time Algorithms for Prime Factorization and Discrete Logarithms on a Quantum Computer , 1995, SIAM Rev..

[32]  Qiang Li,et al.  A hybrid classical-quantum clustering algorithm based on quantum walks , 2011, Quantum Inf. Process..

[33]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[34]  Teofilo F. GONZALEZ,et al.  Clustering to Minimize the Maximum Intercluster Distance , 1985, Theor. Comput. Sci..

[35]  Charles H. Bennett,et al.  Logical reversibility of computation , 1973 .

[36]  Assaf Gottlieb,et al.  Algorithm for data clustering in pattern recognition problems based on quantum mechanics. , 2001, Physical review letters.

[37]  Leonard Pitt,et al.  Sublinear time approximate clustering , 2001, SODA '01.

[38]  Marco Pellegrini,et al.  On computing the diameter of a point set in high dimensional Euclidean space , 1999, Theor. Comput. Sci..

[39]  Seth Lloyd,et al.  Adiabatic quantum computation is equivalent to standard quantum computation , 2004, 45th Annual IEEE Symposium on Foundations of Computer Science.

[40]  Lov K. Grover.  A framework for fast quantum mechanical algorithms , 1997, STOC '98.

[41]  Alain Tapp,et al.  Quantum Entanglement and the Communication Complexity of the Inner Product Function , 1998, QCQC.

[42]  Qiang Li,et al.  A novel clustering algorithm based on quantum games , 2008, ArXiv.

[43]  R Raussendorf,et al.  A one-way quantum computer. , 2001, Physical review letters.

[44]  Christos H. Papadimitriou,et al.  Worst-Case and Probabilistic Analysis of a Geometric Location Problem , 1981, SIAM J. Comput..

[45]  Gilles Brassard,et al.  Strengths and Weaknesses of Quantum Computing , 1997, SIAM J. Comput..

[46]  Ronald de Wolf,et al.  Quantum communication and complexity , 2002, Theor. Comput. Sci..

[47]  Huimin Liu,et al.  Quantum clustering-based weighted linear programming support vector regression for multivariable nonlinear problem , 2010, Soft Comput..

[48]  M. Szegedy,et al.  Quantum Walk Based Search Algorithms , 2008, TAMC.

[49]  Davide Anguita,et al.  Quantum optimization for training support vector machines , 2003, Neural Networks.

[50]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[51]  Gilles Brassard,et al.  Tight bounds on quantum searching , 1996, quant-ph/9605034.

[52]  Gilles Brassard,et al.  Quantum clustering algorithms , 2007, ICML '07.

[53]  Rocco A. Servedio,et al.  Separating Quantum and Classical Learning , 2001, ICALP.

[54]  Gilles Brassard,et al.  An exact quantum polynomial-time algorithm for Simon's problem , 1997, Proceedings of the Fifth Israeli Symposium on Theory of Computing and Systems.

[55]  Clara Pizzuti,et al.  Fast Outlier Detection in High Dimensional Spaces , 2002, PKDD.

[56]  Tzyh Jong Tarn,et al.  Quantum Reinforcement Learning , 2005, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[57]  G. Brassard,et al.  Quantum Pseudo-Telepathy , 2004, quant-ph/0407221.

[58]  S. Lloyd,et al.  Architectures for a quantum random access memory , 2008, 0807.4994.

[59]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[60]  Gilles Brassard,et al.  Quantum Counting , 1998, ICALP.

[61]  David Horn,et al.  The Method of Quantum Clustering , 2001, NIPS.

[62]  Sergei N. Bespamyatnikh.  An efficient algorithm for the three-dimensional diameter problem , 1998, SODA '98.

[63]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[64]  Gilles Brassard,et al.  Machine Learning in a Quantum World , 2006, Canadian AI.

[65]  Hans-Peter Kriegel,et al.  LOF: identifying density-based local outliers , 2000, SIGMOD '00.

[66]  Philip M. Long,et al.  Performance guarantees for hierarchical clustering , 2002, J. Comput. Syst. Sci..

[67]  Andris Ambainis,et al.  QUANTUM WALKS AND THEIR ALGORITHMIC APPLICATIONS , 2003, quant-ph/0403120.