Abstract We propose a method of quantum machine learning called quantum mutual information neural estimation (QMINE) for estimating von Neumann entropy and quantum mutual information, which are fundamental properties in quantum information theory. The QMINE proposed here basically utilizes a technique of quantum neural networks (QNNs), to minimize a loss function that determines the von Neumann entropy, and thus quantum mutual information, which is believed more powerful to process quantum datasets than conventional neural networks due to quantum superposition and entanglement. To create a precise loss function, we propose a quantum Donsker-Varadhan representation (QDVR), which is a quantum analog of the classical Donsker-Varadhan representation. By exploiting a parameter shift rule on parameterized quantum circuits, we can efficiently implement and optimize the QNN and estimate the quantum entropies using the QMINE technique. Furthermore, numerical observations support our predictions of QDVR and demonstrate the good performance of QMINE.
Abstract We propose a method of quantum machine learning called quantum mutual information neural estimation (QMINE) for estimating von Neumann entropy and quantum mutual information, which are fundamental properties in quantum information theory. The QMINE proposed here basically utilizes a technique of quantum neural networks (QNNs), to minimize a loss function that determines the von Neumann entropy, and thus quantum mutual information, which is believed more powerful to process quantum datasets than conventional neural networks due to quantum superposition and entanglement. To create a precise loss function, we propose a quantum Donsker-Varadhan representation (QDVR), which is a quantum analog of the classical Donsker-Varadhan representation. By exploiting a parameter shift rule on parameterized quantum circuits, we can efficiently implement and optimize the QNN and estimate the quantum entropies using the QMINE technique. Furthermore, numerical observations support our predictions of QDVR and demonstrate the good performance of QMINE.
Quantum neural networks (QNNs) is a parameterized quantum circuit model, which can be trained by gradient-based optimizer, can be used for supervised learning, regression tasks, combinatorial optimization, etc. Although many works have demonstrated that QNNs have better learnability, generalizability, etc. compared to classical neural networks. However, as with classical neural networks, we still can't explain their working mechanism well. In this paper, we reveal the training mechanism of QNNs by mutual information. Unlike traditional mutual information in neural networks, due to quantum computing remains information conserved, the mutual information is trivial of the input and output of U operator. In our work, in order to observe the change of mutual information during training, we divide the quantum circuit (U operator) into two subsystems, discard subsystem (D) and measurement subsystem (M) respectively. We calculate two mutual information, I(Di : Mo) and I(Mi : Mo) (i and o means input or output of the corresponding subsystem), and observe their behavior during training. As the epochs increases, I(Di : Mo) gradually increases, this may means some information of discard subsystem is continuously pushed into the measurement subsystem, the information should be label-related. What's more, I(Mi : Mo) exist two-phase behavior in training process, this consistent with the information bottleneck anticipation. The first phase, I(Mi : Mo) is increasing, this means the measurement subsystem perform feature fitting. The second phase, I(Mi : Mo) is decreasing, this may means the system is generalizing, the measurement subsystem discard label-irrelevant information into the discard subsystem as many as possible. Our work discussed the working mechanism of QNNs by mutual information, further, it can be used to analyze the accuracy and generalization of QNNs.
Abstract Analytically continuing the von Neumann entropy from Rényi entropies is a challenging task in quantum field theory. While the n -th Rényi entropy can be computed using the replica method in the path integral representation of quantum field theory, the analytic continuation can only be achieved for some simple systems on a case-by-case basis. In this work, we propose a general framework to tackle this problem using classical and quantum neural networks with supervised learning. We begin by studying several examples with known von Neumann entropy, where the input data is generated by representing TrρAn Tr ρ A n with a generating function. We adopt KerasTuner to determine the optimal network architecture and hyperparameters with limited data. In addition, we frame a similar problem in terms of quantum machine learning models, where the expressivity of the quantum models for the entanglement entropy as a partial Fourier series is established. Our proposed methods can accurately predict the von Neumann and Rényi entropies numerically, highlighting the potential of deep learning techniques for solving problems in quantum information theory.
Abstract In classical information theory, uncommon information refers to the amount of information that is not shared between two messages, and it admits an operational interpretation as the minimum communication cost required to exchange the messages. Extending this notion to the quantum setting, quantum uncommon information is defined as the amount of quantum information necessary to exchange two quantum states. While the value of uncommon information can be computed exactly in the classical case, no direct method is currently known for calculating its quantum analogue. Prior work has primarily focused on deriving upper and lower bounds for quantum uncommon information. In this work, we propose a new approach for estimating these bounds by utilizing the quantum Donsker–Varadhan representation and implementing a gradient-based optimization method. Our results suggest a pathway toward efficient approximation of quantum uncommon information using variational techniques grounded in quantum neural architectures.
Quantum Machine Learning refers to the interdisciplinary area of research, blending principles from quantum physics and machine learning that can process information on quantum computers. Quantum machine learning (QML) intentions to exploit the superposition (qubit can exist in multiple states) property and other effects of quantum mechanics for enhanced efficiency and speed in specific machine learning computations, promising exponential-power superiority in particular computations. This paper focusses on Quantum Machine Learning Models to develop the framework to learn complicated associations within the data through the adjustment of the variational parameters during training. This framework serves as a foundational structure for implementing quantum neural networks, allowing for further experimentation and growth in quantum machine learning applications. It highlights the quantum circuits to process and learn from data in a mode distinct from classical neural networks. As the retrieve of quantum computing grows, such frameworks can be adapted and expanded to explore more sophisticated quantum algorithms and architectures. In the circumstances of Quantum Neural Networks, gradient descents is used in minimizing cost or loss function by iteratively adjusting the variational parameters based onto the gradient of the loss with admire to those parameters. The output that indicates the process of installing the Quantum information science Kit (Qiskit) library in Python specifically version 3.7 along with its dependencies.
Abstract Calculating the von Neumann entanglement entropy from experimental data is challenging due to its dependence on the complete wavefunction, forcing reliance on approximations such as classical mutual information (MI). We propose a machine learning approach using a graph neural network to predict the von Neumann entropy directly from experimentally accessible bitstrings. We test this approach on a Rydberg ladder system and achieve a mean absolute error of 3.6 × 10 − 3 when evaluating within the training range on a dataset with entropy values ranging from 0 to 1.9. The model achieves a mean absolute percentage error of 1.44% and outperforms MI-based bounds. When tested beyond the training range, the model maintains reasonable accuracy. Furthermore, we demonstrate that fine-tuning the model with small datasets significantly improves performance on data outside the original training range.
The remarkable generalization capabilities of overparameterized neural networks remain one of the most profound mysteries in modern machine learning. Despite having sufficient capacity to simply memorize training data, these networks consistently achieve superior performance on unseen test examples. Traditional analyses focusing on weight distributions, loss landscapes, and optimization dynamics have provided partial insights but fail to capture the complex correlational structure that emerges between neurons during learning. This paper introduces a comprehensive quantum information framework for analyzing neural network representations, treating hidden layer activations as quantum states and characterizing them through density matrices, von Neumann entropy, purity, and related quantum information metrics. Through systematic experiments on synthetic classification tasks and algorithmic reasoning problems spanning over 3000 cumulative training epochs and 5000 Wang-Landau sampling iterations, we demonstrate that these quantum metrics reveal structure completely invisible to classical analysis. Our results show that stochastic gradient descent systematically reduces von Neumann entropy while increasing purity as networks learn, transitioning from highly mixed quantum states with entropy approximately 1.42 and purity approximately 0.29 to purer configurations with entropy approximately 1.19 and purity approximately 0.37 that achieve superior test accuracy of 99.5%. Using Wang-Landau sampling to explore the equilibrium entropy landscape, we discover that neural networks naturally favor high-entropy states with entropy approximately 1.42 and moderate accuracy of 62.0%, and that optimization actively purifies the quantum state to achieve task performance. On modular arithmetic tasks exhibiting the grokking phenomenon, we observe that von Neumann entropy increases dramatically from 1.55 to 3.29, representing a 112% increase, during an extended 2000-epoch memorization phase before any improvement in generalization, while purity decreases correspondingly from 0.444 to 0.042, a 90.5% decrease, approaching the maximally mixed limit of 0.01. This entropy accumulation phase appears necessary for eventual generalization, with the network building quantum correlations at a rate of approximately 0.00097 nats per epoch during the plateau. Weight entropy, in contrast, shows minimal change of only 11% increase over the same period. Correlation analysis reveals that von Neumann entropy and purity are almost perfectly anticorrelated with a correlation coefficient of 1 -0.99, while weight entropy shows weak correlation with quantum metrics with absolute correlation coefficients less than 0.3. The effective rank of the density matrix stabilizes near 2.7 to 3.0 for the 6-neuron classifier, indicating that the network effectively uses approximately three independent activation modes. These findings establish quantum information metrics as powerful tools for understanding neural network learning dynamics, provide the first quantitative evidence for the entropy accumulation interpretation of grokking, and suggest that neural networks undergo a quantum-inspired phase transition during learning. We discuss implications for generalization theory, optimization algorithm design, and the statistical physics of deep learning, and outline a comprehensive research agenda for extending these methods to larger architectures and more complex tasks.