Quantum Causal Inference

Anupam Ghosh

Katja Ried, Megan Agnew, L. Vermeyden +3 more

Mohammad Ali Javidian, Vaneet Aggarwal, Fanglin Bao +1 more

Inferring causality from observational data alone is one of the most important and challenging problems in statistical inference. We propose a greedy algorithm for quantum entropic causal inference that unifies classical and quantum causal inference.

Sergey M. Korotaev, Evgeniy O. Kiktenko

Jincheng Zhang

This paper proposes a novel framework for causal inference, termed Quantum Entanglement-Based Distributed Causal Inference (QEBCI), leveraging the unique properties of quantum entanglement to overcome the limitations of traditional causal inference methods in distributed environments. The core concept involves constructing a distributed network of quantum nodes, each storing a portion of causal data. Utilizing entangled states, instantaneous correlations and updates across these nodes are facilitated, enabling the construction of a global causal graph. Furthermore, quantum error correction techniques are integrated to ensure the accuracy of computations. QEBCI offers the potential for high-fidelity, real-time, and distributed causal inference, particularly relevant for complex systems and large-scale datasets where data silos and information latency pose significant challenges. The proposed methodology provides a theoretical foundation and outlines a key mechanism for achieving this. ---

Peter J. Riggs