Quantum classical hybrid neural networks for continuous variable prediction

Paper: arXiv 2212.04209

Authors: Prateek Jain, Alberto Garcia Garcia

Abstract

Within this decade, quantum computers are predicted to outperform conventional computers in terms of processing power and have a disruptive effect on a variety of business sectors. It is predicted that the financial sector would be one of the first to benefit from quantum computing both in the short and long terms. In this research work we use Hybrid Quantum Neural networks to present a quantum machine learning approach for Continuous variable prediction.

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 3.5/10
• Quadrant: Lab Rats — theoretically deep, empirically untested

Why this score: The paper presents an interesting quantum-classical hybrid neural network framework for continuous variable prediction. However, while the theoretical framework and mathematical formulation of quantum machine learning are moderately advanced, the paper relies heavily on general conceptual promises with insufficient empirical validation on robust financial datasets.

Research Flowchart

  flowchart TD
    A[Goal: Predict Continuous Variables via Hybrid Quantum Neural Networks] --> B[Data Input: Financial Cross-Asset Time Series]
    B --> C[Methodology: Encode Classical Data into Quantum States]
    C --> D[Compute: Train Hybrid Quantum-Classical Neural Network]
    D --> E[Outcome: Enhanced Prediction Power for Financial Analytics]