• Corpus ID: 9767785

Training a Binary Classifier with the Quantum Adiabatic Algorithm

@article{Neven2008TrainingAB,
  title={Training a Binary Classifier with the Quantum Adiabatic Algorithm},
  author={Hartmut Neven and Vasil S. Denchev and Geordie Rose and William G. Macready},
  journal={arXiv: Quantum Physics},
  year={2008}
}
This paper describes how to make the problem of binary classification amenable to quantum computing. A formulation is employed in which the binary classifier is constructed as a thresholded linear superposition of a set of weak classifiers. The weights in the superposition are optimized in a learning process that strives to minimize the training error as well as the number of weak classifiers used. No efficient solution to this problem is known. To bring it into a format that allows the… 

Figures from this paper

Training a Large Scale Classifier with the Quantum Adiabatic Algorithm
TLDR
This communication generalizes the baseline method to large scale classifier training and provides theoretical arguments as to why the proposed optimization method is superior to versions of boosting that only minimize the empirical loss.
Robust Classification with Adiabatic Quantum Optimization
TLDR
A non-convex training objective for robust binary classification of data sets in which label noise is present is proposed and validated by using a heuristic classical solver as a stand-in for quantum hardware.
Solving a Higgs optimization problem with quantum annealing for machine learning
TLDR
This work uses quantum and classical annealing (probabilistic techniques for approximating the global maximum or minimum of a given function) to solve a Higgs-signal-versus-background machine learning optimization problem, mapped to a problem of finding the ground state of a corresponding Ising spin model.
Adiabatic quantum linear regression
TLDR
This paper formulate the regression problem as a quadratic unconstrained binary optimization (QUBO) problem, analyze the quantum approach theoretically, test it on the D-Wave adiabatic quantum computer and compare its performance to a classical approach that uses the Scikit-learn library in Python.
Comparisons of Performance between Quantum and Classical Machine Learning
TLDR
The main conclusion was that quantum multi-class SVM classifiers have the potential to be useful in the future as quantum computer's available number of qubits increases.
Quantum adiabatic machine learning
TLDR
This work applies and illustrates this approach to machine learning and anomaly detection via quantum adiabatic evolution in detail to the problem of software verification and validation, with a specific example of the learning phase applied to a problem of interest in flight control systems.
Quantum Annealing Formulation for Binary Neural Networks
TLDR
This work devise a quadratic unconstrained binary optimization formulation for the training problem of binary neural networks, and shows how the problem can be optimized directly on a quantum annealer, thereby opening up to the potential gains of quantum computing.
Digitized adiabatic quantum computing with a superconducting circuit.
TLDR
The demonstration of digitized adiabatic quantum computing in the solid state opens a path to synthesizing long-range correlations and solving complex computational problems.
Adiabatic quantum computation
Adiabatic quantum computing (AQC) started as an approach to solving optimization problems, and has evolved into an important universal alternative to the standard circuit model of quantum computing,
Machine learning & artificial intelligence in the quantum domain: a review of recent progress
TLDR
This review describes the main ideas, recent developments and progress in a broad spectrum of research investigating ML and AI in the quantum domain, and broaches the fundamental issue of quantum generalizations of learning and AI concepts.
...
...

References

SHOWING 1-10 OF 14 REFERENCES
A Quantum Adiabatic Evolution Algorithm Applied to Random Instances of an NP-Complete Problem
TLDR
For the small examples that the authors could simulate, the quantum adiabatic algorithm worked well, providing evidence that quantum computers (if large ones can be built) may be able to outperform ordinary computers on hard sets of instances of NP-complete problems.
Quantum Computation by Adiabatic Evolution
We give a quantum algorithm for solving instances of the satisfiability problem, based on adiabatic evolution. The evolution of the quantum state is governed by a time-dependent Hamiltonian that
Multistart Tabu Search Strategies for the Unconstrained Binary Quadratic Optimization Problem
TLDR
Five rather different multistart tabu search strategies for the unconstrained binary quadratic optimization problem are described and experimentally compared: a random restart procedure, an application of a deterministic heuristic to specially constructed subproblems, anApplication of a randomized procedure to the full problem, a constructive procedure usingtabu search adaptive memory, and an approach based on solving perturbed problems.
On the Density of Families of Sets
  • N. Sauer
  • Mathematics
    J. Comb. Theory, Ser. A
  • 1972
Solving quadratic (0,1)-problems by semidefinite programs and cutting planes
We present computational experiments for solving quadratic (0, 1) problems. Our approach combines a semidefinite relaxation with a cutting plane technique, and is applied in a Branch and Bound
A Short Introduction to Boosting
TLDR
This short overview paper introduces the boosting algorithm AdaBoost, and explains the underlying theory of boosting, including an explanation of why boosting often does not suffer from overfitting as well as boosting’s relationship to support-vector machines.
Use of the Zero-Norm with Linear Models and Kernel Methods
A blow-molded thermoplastic can has front and side walls and a nozzle integral therewith. The nozzle leads into a quarter-moon-shaped, force-absorbing protuberance in the wall of the can directed
GML AdaBoost Matlab toolbox 0.3. MSU Graphics & Media Lab
  • GML AdaBoost Matlab toolbox 0.3. MSU Graphics & Media Lab
  • 2006
...
...