Quantum-assisted associative adversarial network: applying quantum annealing in deep learning

We present an algorithm for learning a latent variable generative model via generative adversarial learning where the canonical uniform noise input is replaced by samples from a graphical model. This graphical model is learned by a Boltzmann machine which learns low-dimensional feature representation of data extracted by the discriminator. A quantum annealer, the D-Wave 2000Q, is used to sample from this model. This algorithm joins a growing family of algorithms that use a quantum annealing subroutine in deep learning, and provides a framework to test the advantages of quantum-assisted learning in GANs. Fully connected, symmetric bipartite and Chimera graph topologies are compared on a reduced stochastically binarized MNIST dataset, for both classical and quantum annealing sampling methods. The quantum-assisted associative adversarial network successfully learns a generative model of the MNIST dataset for all topologies, and is also applied to the LSUN dataset bedrooms class for the Chimera topology. Evaluated using the Frechet inception distance and inception score, the quantum and classical versions of the algorithm are found to have equivalent performance for learning an implicit generative model of the MNIST dataset.

[1]  Jacob biamonte,et al.  Quantum machine learning , 2016, Nature.

[2]  M. Benedetti,et al.  Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning , 2015, 1510.07611.

[3]  Daniel A. Lidar,et al.  Quantum adiabatic Markovian master equations , 2012, 1206.4197.

[4]  Daniel A. Lidar,et al.  Optimally Stopped Optimization , 2016, 1608.05764.

[5]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[6]  Simone Severini,et al.  Quantum machine learning: a classical perspective , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[7]  Terrence J. Sejnowski,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cognitive Sciences.

[8]  Asli Çelikyilmaz,et al.  Associative Adversarial Networks , 2016, ArXiv.

[9]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Ashley Montanaro,et al.  Average-case complexity versus approximate simulation of commuting quantum computations , 2015, Physical review letters.

[11]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[12]  Alejandro Perdomo-Ortiz,et al.  Quantum-assisted Helmholtz machines: A quantum–classical deep learning framework for industrial datasets in near-term devices , 2017, ArXiv.

[13]  Eleanor G. Rieffel,et al.  Thermalization, Freeze-out, and Noise: Deciphering Experimental Quantum Annealers , 2017, 1703.03902.

[14]  Walter Vinci,et al.  Quantum variational autoencoder , 2018, Quantum Science and Technology.

[15]  Jack Raymond,et al.  Global Warming: Temperature Estimation in Annealers , 2016, Front. ICT.

[16]  M. Amin.  Searching for quantum speedup in quasistatic quantum annealers , 2015, 1503.04216.

[17]  Shakir Mohamed,et al.  Learning in Implicit Generative Models , 2016, ArXiv.

[18]  Truyen Tran,et al.  On catastrophic forgetting and mode collapse in Generative Adversarial Networks , 2018, ArXiv.

[19]  Eleanor G. Rieffel,et al.  Perils of embedding for sampling problems , 2020, Physical Review Research.

[20]  Nicolas Le Roux,et al.  Representational Power of Restricted Boltzmann Machines and Deep Belief Networks , 2008, Neural Computation.

[21]  Ben Taskar,et al.  Graphical Models in a Nutshell , 2007 .

[22]  Rupak Biswas,et al.  A NASA perspective on quantum computing: Opportunities and challenges , 2017, Parallel Comput..

[23]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[24]  Rupak Biswas,et al.  Quantum-Assisted Learning of Hardware-Embedded Probabilistic Graphical Models , 2016, 1609.02542.

[25]  Andrew McCallum,et al.  Introduction to Statistical Relational Learning , 2007 .

[26]  E. Rieffel,et al.  Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers , 2018, Physical Review Applied.

[27]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[28]  Daniel A. Lidar,et al.  Defining and detecting quantum speedup , 2014, Science.

[29]  Miguel Á. Carreira-Perpiñán,et al.  On Contrastive Divergence Learning , 2005, AISTATS.

[30]  Steven H. Adachi,et al.  Application of Quantum Annealing to Training of Deep Neural Networks , 2015, ArXiv.

[31]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[32]  Roger Melko,et al.  Quantum Boltzmann Machine , 2016, 1601.02036.

[33]  Tom White,et al.  Sampling Generative Networks: Notes on a Few Effective Techniques , 2016, ArXiv.

[34]  Fei-Yue Wang,et al.  Generative adversarial networks: introduction and outlook , 2017, IEEE/CAA Journal of Automatica Sinica.

[35]  Michael J. Bremner,et al.  Quantum sampling problems, BosonSampling and quantum supremacy , 2017, npj Quantum Information.

[36]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[37]  Samuel A. Barnett,et al.  Convergence Problems with Generative Adversarial Networks (GANs) , 2018, ArXiv.

[38]  Shing-Chow Chan,et al.  A cumulant-based approach for direction finding in the presence of mutual coupling , 2014, Signal Process..

[39]  Hilbert J Kappen,et al.  Learning quantum models from quantum or classical data , 2018, Journal of Physics A: Mathematical and Theoretical.

[40]  Vicky Choi,et al.  Minor-embedding in adiabatic quantum computation: II. Minor-universal graph design , 2010, Quantum Inf. Process..

[41]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[42]  Rupak Biswas,et al.  Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers , 2017, Quantum Science and Technology.

[43]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[44]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

[45]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[46]  Firas Hamze,et al.  Glassy Chimeras could be blind to quantum speedup: Designing better benchmarks for quantum annealing machines , 2014, 1401.1546.