2019

Generative training of quantum Boltzmann machines with hidden units

Wiebe, Nathan, Wossnig, Leonard

Understand

In this article we provide a method for fully quantum generative training of quantum Boltzmann machines with both visible and hidden units while using quantum relative entropy as an objective.

This is significant because prior methods were not able to do so due to mathematical challenges posed by the gradient evaluation.
We present two novel methods for solving this problem.
The first proposal addresses it, for a class of restricted quantum Boltzmann machines with mutually commuting Hamiltonians on the hidden units, by using a variational upper bound on the quantum relative entropy.

Built on

Statistical physics, vol. 5
LD Landau and EM Lifshitz · 1980
Earlier work this paper cites.
Simulated annealing and boltzmann machines
Emile Aarts and Jan Korst · 1988
Earlier work this paper cites.
Strategies and networks for state-dependent quantum cloning
Anthony Chefles and Stephen M Barnett · 1999
Earlier work this paper cites.
Quantum amplitude amplification and estimation
Gilles Brassard, Peter Hoyer, Michele Mosca, and Alain Tapp · 2002
Earlier work this paper cites.
Equivalences and separations between quantum and classical learnability
Rocco A Servedio and Steven J Gortler · 2004
Earlier work this paper cites.
Restricted boltzmann machines for collaborative filtering
Ruslan Salakhutdinov, Andriy Mnih, and Geoffrey Hinton · 2007
Earlier work this paper cites.
Efficient quantum algorithms for simulating sparse hamiltonians
Dominic W Berry, Graeme Ahokas, Richard Cleve, and Barry C Sanders · 2007
Earlier work this paper cites.
Training restricted boltzmann machines using approximations to the likelihood gradient
Tijmen Tieleman · 2008
Earlier work this paper cites.
Representational power of restricted boltzmann machines and deep belief networks
Nicolas Le Roux and Yoshua Bengio · 2008
Earlier work this paper cites.
Functions of matrices: theory and computation
Nicholas J Higham · 2008
Earlier work this paper cites.
Deep boltzmann machines
Ruslan Salakhutdinov and Geoffrey Hinton · 2009
Earlier work this paper cites.
Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations
Honglak Lee, Roger Grosse, Rajesh Ranganath, and Andrew Y Ng · 2009
Earlier work this paper cites.
Unsupervised feature learning for audio classification using convolutional deep belief networks
Honglak Lee, Peter Pham, Yan Largman, and Andrew Y Ng · 2009
Earlier work this paper cites.
A polynomial quantum algorithm for approximating the jones polynomial
Dorit Aharonov, Vaughan Jones, and Zeph Landau · 2009
Earlier work this paper cites.
Sampling from the thermal quantum gibbs state and evaluating partition functions with a quantum computer
David Poulin and Pawel Wocjan · 2009
Earlier work this paper cites.

Similar

Efficient learning of deep boltzmann machines
Ruslan Salakhutdinov and Hugo Larochelle · 2010
Cited alongside, same era.
Acoustic modeling using deep belief networks
Abdel-rahman Mohamed, George E Dahl, and Geoffrey Hinton · 2011
Cited alongside, same era.
A practical guide to training restricted boltzmann machines
Geoffrey E Hinton · 2012
Cited alongside, same era.
Multimodal learning with deep boltzmann machines
Nitish Srivastava and Ruslan R Salakhutdinov · 2012
Cited alongside, same era.
A quantum–quantum metropolis algorithm
Man-Hong Yung and Alán Aspuru-Guzik · 2012
Cited alongside, same era.
Quantum algorithms for supervised and unsupervised machine learning
Original
Seth Lloyd, Masoud Mohseni, and Patrick Rebentrost · 2013
Cited alongside, same era.
Quantum principal component analysis
Seth Lloyd, Masoud Mohseni, and Patrick Rebentrost · 2014
Cited alongside, same era.
Reinforcement learning using quantum boltzmann machines
Original
Daniel Crawford, Anna Levit, Navid Ghadermarzy, Jaspreet S Oberoi, and Pooya Ronagh · 2016
Cited alongside, same era.
Learning thermodynamics with boltzmann machines
Giacomo Torlai and Roger G Melko · 2016
Cited alongside, same era.
Quantum algorithms for gibbs sampling and hitting-time estimation
Original
Anirban Narayan Chowdhury and Rolando D Somma · 2016
Cited alongside, same era.
Quantum machine learning
Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patrick Rebentrost, Nathan Wiebe, and Seth Lloyd · 2017
Cited alongside, same era.
Tomography and generative training with quantum boltzmann machines
Mária Kieferová and Nathan Wiebe · 2017
Cited alongside, same era.

Then

Restricted boltzmann machine learning for solving strongly correlated quantum systems
Yusuke Nomura, Andrew S Darmawan, Youhei Yamaji, and Masatoshi Imada · 2017
Later among the works it cites.
Quantum sdp-solvers: Better upper and lower bounds
Joran Van Apeldoorn, András Gilyén, Sander Gribling, and Ronald de Wolf · 2017
Later among the works it cites.
Hamiltonian simulation with optimal sample complexity
Shelby Kimmel, Cedric Yen-Yu Lin, Guang Hao Low, Maris Ozols, and Theodore J Yoder · 2017
Later among the works it cites.
Quantum machine learning: a classical perspective
Carlo Ciliberto, Mark Herbster, Alessandro Davide Ialongo, Massimiliano Pontil, Andrea Rocchetto, Simone Severini, and Leonard Wossnig · 2018
Later among the works it cites.
Optimal quantum sample complexity of learning algorithms
Srinivasan Arunachalam and Ronald De Wolf · 2018
Later among the works it cites.
Barren plateaus in quantum neural network training landscapes
Jarrod R McClean, Sergio Boixo, Vadim N Smelyanskiy, Ryan Babbush, and Hartmut Neven · 2018
Later among the works it cites.
Circuit-centric quantum classifiers
Original
Maria Schuld, Alex Bocharov, Krysta Svore, and Nathan Wiebe · 2018
Later among the works it cites.
Learning quantum models from quantum or classical data
Original
Hilbert J Kappen · 2018
Later among the works it cites.
Quantum boltzmann machine
Mohammad H Amin, Evgeny Andriyash, Jason Rolfe, Bohdan Kulchytskyy, and Roger Melko · 2018
Later among the works it cites.
Notes on the matrix exponential and logarithm
Howard E Haber · 2018
Later among the works it cites.
Quantum language processing
Original
Nathan Wiebe, Alex Bocharov, Paul Smolensky, Krysta Svore, and Matthias Troyer · 2019
Closest in time.
Quantum machine learning in feature hilbert spaces
Maria Schuld and Nathan Killoran · 2019
Closest in time.
Adversarial quantum circuit learning for pure state approximation
Marcello Benedetti, Edward Grant, Leonard Wossnig, and Simone Severini · 2019
Closest in time.
Optimizing quantum optimization algorithms via faster quantum gradient computation
András Gilyén, Srinivasan Arunachalam, and Nathan Wiebe · 2019
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…