The recently proposed Quantum Neuron Born Machine (QNBM) has demonstrated quality initial performance as the first quantum generative machine learning (ML) model proposed with non-linear activations. However, previous investigations have been limited in scope with regards to the model's learnability and simulatability. In this work, we make a considerable leap forward by providing an extensive deep dive into the QNBM's potential as a generative model. We first demonstrate that the QNBM's network representation makes it non-trivial to be classically efficiently simulated. Following this result, we showcase the model's ability to learn (express and train on) a wider set of probability distributions, and benchmark the performance against a classical Restricted Boltzmann Machine (RBM). The QNBM is able to outperform this classical model on all distributions, even for the most optimally trained RBM among our simulations. Specifically, the QNBM outperforms the RBM with an improvement factor of 75.3x, 6.4x, and 3.5x for the discrete Gaussian, cardinality-constrained, and Bars and Stripes distributions respectively. Lastly, we conduct an initial investigation into the model's generalization capabilities and use a KL test to show that the model is able to approximate the ground truth probability distribution more closely than the training distribution when given access to a limited amount of data. Overall, we put forth a stronger case in support of using the QNBM for larger-scale generative tasks.

Due to the linearity of quantum mechanics, it remains a challenge to design quantum generative machine learning models that embed non-linear activations into the evolution of the statevector. However, some of the most successful classical generative models, such as those based on neural networks, involve highly non-linear dynamics for quality training. In this paper, we explore the effect of these dynamics in quantum generative modeling by introducing a model that adds non-linear activations via a neural network structure onto the standard Born Machine framework - the Quantum Neuron Born Machine (QNBM). To achieve this, we utilize a previously introduced Quantum Neuron subroutine, which is a repeat-until-success circuit with mid-circuit measurements and classical control. After introducing the QNBM, we investigate how its performance depends on network size, by training a 3-layer QNBM with 4 output neurons and various input and hidden layer sizes. We then compare our non-linear QNBM to the linear Quantum Circuit Born Machine (QCBM). We allocate similar time and memory resources to each model, such that the only major difference is the qubit overhead required by the QNBM. With gradient-based training, we show that while both models can easily learn a trivial uniform probability distribution, on a more challenging class of distributions, the QNBM achieves an almost 3x smaller error rate than a QCBM with a similar number of tunable parameters. We therefore provide evidence that suggests that non-linearity is a useful resource in quantum generative models, and we put forth the QNBM as a new model with good generative performance and potential for quantum advantage.

Tensor networks are used to efficiently approximate states of strongly-correlated quantum many-body systems. More generally, tensor network approximations may allow to reduce the costs for operating on an order-NN tensor from exponential to polynomial in NN, and this has become a popular approach for machine learning. We introduce the idea of imposing low-rank constraints on the tensors that compose the tensor network. With this modification, the time and space complexities for the network optimization can be substantially reduced while maintaining high accuracy. We detail this idea for tree tensor network states (TTNS) and projected entangled-pair states.