There is a long way to go before quantum information (QI) can have a real-world impact on machine learning applications. However, in the short term, QI presents a principled approach to unravel performance bounds and find hidden quantum-classical parallels for widely used machine learning algorithms.
[Check out this paper, if you are interested in causal inference]
"Identification of Latent Graphs: A Quantum Entropic Approach," Neurips Workshop on Causal Inference & Machine Learning WHY-21, Dec. 2021 Mohammad Ali Javidian, Vaneet Aggarwal, and Zubin Jacob,
[Check out this paper on training a large number of qubits for quantum machine learning if you work in the field of variational quantum circuits and/or tensor networks]
"Tensor Ring Parametrized Variational Quantum Circuits for Large Scale Quantum Machine Learning," Neurips Workshop on Quantum Tensor Networks in Machine Learning, Dec. 2021 Dheeraj Pedirredy, Vipul Bansal, Zubin Jacob, and Vaneet Aggarwal
[Here we explore a quantum generalization of Hidden Markov Models which are routinely used in speed recognition]
"Tensor Rings for Learning Circular Hidden Markov Models," Neurips Workshop on Quantum Tensor Networks in Machine Learning, Dec. 2021 Mohammad Ali Javidian, Vaneet Aggarwal, and Zubin Jacob