Quantum Fair Machine Learning

@article{Perrier2021QuantumFM,
  title={Quantum Fair Machine Learning},
  author={Elija Perrier},
  journal={Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society},
  year={2021}
}
  • Elija Perrier
  • Published 1 February 2021
  • Computer Science
  • Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society
In this paper, we inaugurate the field of quantum fair machine learning. We undertake a comparative analysis of differences and similarities between classical and quantum fair machine learning algorithms, specifying how the unique features of quantum computation alter measures, metrics and remediation strategies when quantum algorithms are subject to fairness constraints. We present the first results in quantum fair machine learning by demonstrating the use of Grover's search algorithm to… 

Figures and Tables from this paper

Ethical Quantum Computing: A Roadmap

This paper presents a roadmap for ethical quantum computing (and quantum information processing more generally) that sets out prospective research programmes and summarises the key elements of quantum informationprocessing relevant to ethical analysis and set-out taxonomies for use by researchers considering the ethics of quantum technologies.

Artificial Intelligence Computing at the Quantum Level

This paper provides a thorough examination of quantum computing from the perspective of a physicist to give laypeople and scientists a broad but in-depth understanding of the area.

The Quantum Governance Stack: Models of Governance for Quantum Information Technologies

The emergence of quantum information technologies with potential application across diverse industrial, consumer and technical domains has thrown into relief the need for practical approaches to…

Democratization of Quantum Technologies

As quantum technologies (QT) have been becoming more and more realized, their potential impact on and relation with society has been developing into a pressing issue for exploration. In this paper,…

Exploring bias and fairness in artificial intelligence and machine learning algorithms

This paper investigates if there is any bias present in the benchmark Statlog β€œAustralian Credit Approval” dataset and takes necessary measures to mitigate the bias presentIn this paper, the AIF360 tool can identify and mitigate bias in the data and eventually in the learning algorithms.

References

SHOWING 1-10 OF 36 REFERENCES

Ethical Quantum Computing: A Roadmap

This paper presents a roadmap for ethical quantum computing (and quantum information processing more generally) that sets out prospective research programmes and summarises the key elements of quantum informationprocessing relevant to ethical analysis and set-out taxonomies for use by researchers considering the ethics of quantum technologies.

Characterizing quantum supremacy in near-term devices

A critical question for quantum computing in the near future is whether quantum devices without error correction can perform a well-defined computational task beyond the capabilities of…

Quantum Perceptron Models

Two quantum algorithms for perceptron learning are developed that demonstrate how quantum computation can provide non-trivial improvements in the computational and statistical complexity of the perceptron model.

Quantum Computation and Quantum Information (10th Anniversary edition)

Containing a wealth of figures and exercises, this well-known textbook is ideal for courses on the subject, and will interest beginning graduate students and researchers in physics, computer science, mathematics, and electrical engineering.

An exact quantum polynomial-time algorithm for Simon's problem

  • G. BrassardP. HΓΈyer
  • Computer Science, Mathematics
    Proceedings of the Fifth Israeli Symposium on Theory of Computing and Systems
  • 1997
It is shown that there is a decision problem that can be solved in exact quantum polynomial time, which would require expected exponential time on any classical bounded-error probabilistic computer if the data is supplied as a black box.

Machine Learning in a Quantum World

An investigation of the encounter of ML with QIP is initiated by defining and studying novel learning tasks that correspond to Machine Learning in a world in which the information is fundamentally quantum mechanical.

Quantum noise protects quantum classifiers against adversaries

By taking advantage of depolarisation noise in quantum circuits for classification, a robustness bound against adversaries can be derived where the robustness improves with increasing noise, which is the first quantum protocol that can be used against the most general adversaries.

Fault-Tolerant Quantum Computation

Fault tolerance techniques will be essential for achieving the considerable potential of quantum computers and will need to control high noise rates and do so with low overhead, since qubits are expensive.

An Empirical Study of Rich Subgroup Fairness for Machine Learning

In general, the Kearns et al. algorithm converges quickly, large gains in fairness can be obtained with mild costs to accuracy, and that optimizing accuracy subject only to marginal fairness leads to classifiers with substantial subgroup unfairness.

Review of Mathematical frameworks for Fairness in Machine Learning

A review of the main fairness definitions and fair learning methodologies proposed in the literature over the last years is presented from a mathematical point of view and novel results giving the expressions of the optimal fair classifier and the optimalFair predictor in the sense of $\textit{equality of odds}$ are presented.