Application of Quantum Annealing to Training of Deep Neural Networks
arXiv:1510.06356
Abstract
In Deep Learning, a well-known approach for training a Deep Neural Network starts by training a generative Deep Belief Network model, typically using Contrastive Divergence (CD), then fine-tuning the weights using backpropagation or other discriminative techniques. However, the generative training can be time-consuming due to the slow mixing of Gibbs sampling. We investigated an alternative approach that estimates model expectations of Restricted Boltzmann Machines using samples from a D-Wave quantum annealing machine. We tested this method on a coarse-grained version of the MNIST data set. In our tests we found that the quantum sampling-based training approach achieves comparable or better accuracy with significantly fewer iterations of generative training than conventional CD-based training. Further investigation is needed to determine whether similar improvements can be achieved for other data sets, and to what extent these improvements can be attributed to quantum effects.
18 pages
References in corpus (2)
Cited by in corpus (65)
- Quantum Machine Learning
- Machine learning and the physical sciences
- Adiabatic Quantum Computing
- Quantum computing for finance: overview and prospects
- Quantum machine learning: a classical perspective
- Machine Learning Topological States
- Opportunities and challenges for quantum-assisted machine learning in near-term quantum computers
- Estimation of effective temperatures in quantum annealers for sampling applications: A case study with possible applications in deep learning
- Support vector machines on the D-Wave quantum annealer
- Tomography and Generative Data Modeling via Quantum Boltzmann Training
- A full-stack view of probabilistic computing with p-bits: devices, architectures and algorithms
- Prospects for Quantum Enhancement with Diabatic Quantum Annealing
- Power of Pausing: Advancing Understanding of Thermalization in Experimental Quantum Annealers
- A NASA Perspective on Quantum Computing: Opportunities and Challenges
- Improving solutions by embedding larger subproblems in a D-Wave quantum annealer
- Quantum-assisted Helmholtz machines: A quantum-classical deep learning framework for industrial datasets in near-term devices
- Memcomputing: Leveraging memory and physics to compute efficiently
- Adiabatic Quantum Linear Regression
- Classification with Quantum Machine Learning: A Survey
- Temperature scaling law for quantum annealing optimizers
- Quantum Computing Assisted Deep Learning for Fault Detection and Diagnosis in Industrial Process Systems
- A Direct Mapping of Max k-SAT and High Order Parity Checks to a Chimera Graph
- Training and Classification using a Restricted Boltzmann Machine on the D-Wave 2000Q
- Variational inference with a quantum computer
- Polymer Physics by Quantum Computing
- Advances in Quantum Deep Learning: An Overview
- Towards Feature Selection for Ranking and Classification Exploiting Quantum Annealers
- Machine learning \& artificial intelligence in the quantum domain
- Towards Quantum Belief Propagation for LDPC Decoding in Wireless Networks
- Quantum neural networks to simulate many-body quantum systems
- Quantum Enhanced Inference in Markov Logic Networks
- Simulated Quantum Annealing with Two All-to-All Connectivity Schemes
- Scalable effective temperature reduction for quantum annealers via nested quantum annealing correction
- Equation Planting: A Tool for Benchmarking Ising Machines
- Entanglement-based quantum deep learning
- High-Dimensional Similarity Search with Quantum-Assisted Variational Autoencoder
- Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines
- Exploring Unsupervised Anomaly Detection with Quantum Boltzmann Machines in Fraud Detection
- Discriminating Quantum States with Quantum Machine Learning
- Quantum annealing with twisted fields
- Preparing ground states of the XXZ model using the quantum annealing with inductively coupled superconducting flux qubits
- Towards Transfer Learning for Large-Scale Image Classification Using Annealing-based Quantum Boltzmann Machines
- Perils of Embedding for Quantum Sampling
- Accelerating equilibrium spin-glass simulations using quantum annealers via generative deep learning
- Efficient quantum and simulated annealing of Potts models using a half-hot constraint
- Modernizing Quantum Annealing II: Genetic algorithms with the Inference Primitive Formalism
- Geometry and symmetry in quantum Boltzmann machine
- Quantum walk on a chimera graph
- Applications of Quantum Annealing in Statistics
- Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer
- Polynomial unconstrained binary optimisation inspired by optical simulation
- Decoding quantum error correction with Ising model hardware
- Towards Sampling from Nondirected Probabilistic Graphical models using a D-Wave Quantum Annealer
- Sampling Problems on a Quantum Computer
- Systematic comparison of deep belief network training using quantum annealing vs. classical techniques
- Limits of Short-Time Evolution of Local Hamiltonians
- An Overview of Approaches to Modernize Quantum Annealing Using Local Searches
- Stochastic Characteristics of Qubits and Qubit chains on the D-Wave 2X
- Mapping NP-Hard Problems to Restricted Adiabatic Quantum Architectures
- Defining Quantum Neural Networks via Quantum Time Evolution
- Adiabatic Quantum Graph Matching with Permutation Matrix Constraints
- A QUBO Model for Gaussian Process Variance Reduction
- An Amalgamation of Classical and Quantum Machine Learning For the Classification of Adenocarcinoma and Squamous Cell Carcinoma Patients
- Analog Errors in Quantum Annealing: Doom and Hope
- Comparison of D-Wave Quantum Annealing and Classical Simulated Annealing for Local Minima Determination