Project Description:

The class of problems in causal inference which seeks to isolate causal correlations solely from observational data even without interventions has come to the forefront of machine learning, neuroscience, and social sciences. We put forth a theoretical framework for merging quantum information science and causal inference by exploiting entropic principles. The goal of this project is to provide scalable quantum causal inference techniques that can be used to improve learning and inference in classical causal models. To address these problems, we scale up the quantum entropic causal inference approach proposed in (Javidian et al. 2021a, Javidian et al. 2021b) and adopt the proposed tensor network frame work in (Javidian et al. , 2022; Glasser, Sweke et al. 2019).

Start Date:

Mar 1, 2023

Postdoc Qualifications:

The PhD candidate should ideally be a PhD in ECE/CS/Stats or related areas, and have knowledge about probability and linear algebra and some background in the related areas of the project.

Co-Advisors:

Vaneet Aggarwal, IE, vaneet@purdue.edu
Zubin Jacob, ECE, zjacob@purdue.edu

Bibliography:

Glasser, I., R. Sweke, N. Pancotti, J. Eisert and I. Cirac (2019). "Expressive power of tensor-network factorizations for probabilistic modeling." Advances in neural information processing systems 32.
Javidian, M. A., V. Aggarwal, F. Bao and Z. Jacob (2021). Quantum entropic causal inference. Quantum Information and Measurement, Optical Society of America.
Javidian, M. A., V. Aggarwal and Z. Jacob "Identification of Latent Graphs: A Quantum Entropic Approach."
Javidian, M. A., V. Aggarwal and Z. Jacob "Tensor Rings for Learning Circular Hidden Markov Models."