# Certainty In, Certainty Out: REVQCs for Quantum Machine Learning

arXiv: https://arxiv.org/abs/2310.10629 · HTML: https://mlsanity.com/paper/2310.10629/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 16 Oct 2023.

## Builds on (most cited first, 8 of 8)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Robust data encodings for quantum classifiers](https://mlsanity.com/paper/2003.01695/) (2020)
- [Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications](https://mlsanity.com/paper/2309.13207/) (2023)
- [Deep Evidential Learning for Bayesian Quantile Regression](https://mlsanity.com/paper/2308.10650/) (2023)
- [Epistemic Modeling Uncertainty of Rapid Neural Network Ensembles for Adaptive Learning](https://mlsanity.com/paper/2309.06628/) (2023)
- [Evidential uncertainty sampling for active learning](https://mlsanity.com/paper/2309.12494/) (2023)

## Abstract (arXiv)

The field of Quantum Machine Learning (QML) has emerged recently in the hopes of finding new machine learning protocols or exponential speedups for classical ones. Apart from problems with vanishing gradients and efficient encoding methods, these speedups are hard to find because the sampling nature of quantum computers promotes either simulating computations classically or running them many times on quantum computers in order to use approximate expectation values in gradient calculations. In this paper, we make a case for setting high single-sample accuracy as a primary goal. We discuss the statistical theory which enables highly accurate and precise sample inference, and propose a method of reversed training towards this end. We show the effectiveness of this training method by assessing several effective variational quantum circuits (VQCs), trained in both the standard and reversed directions, on random binary subsets of the MNIST and MNIST Fashion datasets, on which our method provides an increase of 10-15% in single-sample inference accuracy.