Hierarchical Learning for Quantum ML: Novel Training Technique for Large-Scale Variational Quantum Circuits

• URL: http://arxiv.org/abs/2311.12929v1
• Date: Tue, 21 Nov 2023 19:00:03 GMT
• Title: Hierarchical Learning for Quantum ML: Novel Training Technique for Large-Scale Variational Quantum Circuits
• Authors: Hrant Gharibyan, Vincent Su, Hayk Tepanyan
• Abstract summary: hierarchical learning is a novel variational architecture for efficient training of large-scale variational quantum circuits. We show that the most significant (qu)bits have a greater effect on the final distribution and can be learned first. This is the first practical demonstration of variational learning on large numbers of qubits.
• Score: 0.6906005491572401
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present hierarchical learning, a novel variational architecture for efficient training of large-scale variational quantum circuits. We test and benchmark our technique for distribution loading with quantum circuit born machines (QCBMs). With QCBMs, probability distributions are loaded into the squared amplitudes of computational basis vectors represented by bitstrings. Our key insight is to take advantage of the fact that the most significant (qu)bits have a greater effect on the final distribution and can be learned first. One can think of it as a generalization of layerwise learning, where some parameters of the variational circuit are learned first to prevent the phenomena of barren plateaus. We briefly review adjoint methods for computing the gradient, in particular for loss functions that are not expectation values of observables. We first compare the role of connectivity in the variational ansatz for the task of loading a Gaussian distribution on nine qubits, finding that 2D connectivity greatly outperforms qubits arranged on a line. Based on our observations, we then implement this strategy on large-scale numerical experiments with GPUs, training a QCBM to reproduce a 3-dimensional multivariate Gaussian distribution on 27 qubits up to $\sim4\%$ total variation distance. Though barren plateau arguments do not strictly apply here due to the objective function not being tied to an observable, this is to our knowledge the first practical demonstration of variational learning on large numbers of qubits. We also demonstrate hierarchical learning as a resource-efficient way to load distributions for existing quantum hardware (IBM's 7 and 27 qubit devices) in tandem with Fire Opal optimizations.

Related papers

• Efficient Learning for Linear Properties of Bounded-Gate Quantum Circuits [63.733312560668274]
  Given a quantum circuit containing d tunable RZ gates and G-d Clifford gates, can a learner perform purely classical inference to efficiently predict its linear properties? We prove that the sample complexity scaling linearly in d is necessary and sufficient to achieve a small prediction error, while the corresponding computational complexity may scale exponentially in d. We devise a kernel-based learning model capable of trading off prediction error and computational complexity, transitioning from exponential to scaling in many practical settings.
  arXiv  Detail & Related papers  (2024-08-22T08:21:28Z)
• Projected Stochastic Gradient Descent with Quantum Annealed Binary Gradients [51.82488018573326]
  We present QP-SBGD, a novel layer-wise optimiser tailored towards training neural networks with binary weights. BNNs reduce the computational requirements and energy consumption of deep learning models with minimal loss in accuracy. Our algorithm is implemented layer-wise, making it suitable to train larger networks on resource-limited quantum hardware.
  arXiv  Detail & Related papers  (2023-10-23T17:32:38Z)
• Quantum state preparation for bell-shaped probability distributions using deconvolution methods [0.0]
  We present a hybrid classical-quantum approach to load quantum data. We use the Jensen-Shannon distance as the cost function to quantify the closeness of the outcome from the classical step and the target distribution. The output from the deconvolution step is used to construct the quantum circuit required to load the given probability distribution.
  arXiv  Detail & Related papers  (2023-10-08T06:55:47Z)
• A hybrid quantum-classical classifier based on branching multi-scale entanglement renormalization ansatz [5.548873288570182]
  This paper proposes a quantum semi-supervised classifier based on label propagation. Considering the difficulty of graph construction, we develop a variational quantum label propagation (VQLP) method. In this method, a locally parameterized quantum circuit is created to reduce the parameters required in the optimization.
  arXiv  Detail & Related papers  (2023-03-14T13:46:45Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Protocols for Trainable and Differentiable Quantum Generative Modelling [21.24186888129542]
  We propose an approach for learning probability distributions as differentiable quantum circuits (DQC) We perform training of a DQC-based model, where data is encoded in a latent space with a phase feature map, followed by a variational quantum circuit. This allows fast sampling from parametrized distributions using a single-shot readout.
  arXiv  Detail & Related papers  (2022-02-16T18:55:48Z)
• Tensor Ring Parametrized Variational Quantum Circuits for Large Scale Quantum Machine Learning [28.026962110693695]
  We propose an algorithm that compresses the quantum state within the circuit using a tensor ring representation. The storage and computational time increases linearly in the number of qubits and number of layers, as compared to the exponential increase with exact simulation algorithms. We achieve a test accuracy of 83.33% on Iris dataset and a maximum of 99.30% and 76.31% on binary and ternary classification of MNIST dataset.
  arXiv  Detail & Related papers  (2022-01-21T19:54:57Z)
• Generative Quantum Learning of Joint Probability Distribution Functions [1.221966660783828]
  We design quantum machine learning algorithms to model copulas. We show that any copula can be naturally mapped to a multipartite maximally entangled state. A variational ansatz we christen as a qopula' creates arbitrary correlations between variables.
  arXiv  Detail & Related papers  (2021-09-13T20:50:15Z)
• Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss [61.26793005355441]
  Cluster-Promoting Quantization (CPQ) finds the optimal quantization grids for neural networks. DropBits is a new bit-drop technique that revises the standard dropout regularization to randomly drop bits instead of neurons. We experimentally validate our method on various benchmark datasets and network architectures.
  arXiv  Detail & Related papers  (2021-09-05T15:15:07Z)
• A quantum algorithm for training wide and deep classical neural networks [72.2614468437919]
  We show that conditions amenable to classical trainability via gradient descent coincide with those necessary for efficiently solving quantum linear systems. We numerically demonstrate that the MNIST image dataset satisfies such conditions. We provide empirical evidence for $O(log n)$ training of a convolutional neural network with pooling.
  arXiv  Detail & Related papers  (2021-07-19T23:41:03Z)
• Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks [73.29587731448345]
  This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existing methods obtain the quantized weights by performing quantization on the full-precision network weights. Second, to obtain low bit-width activations, existing works consider all channels equally.
  arXiv  Detail & Related papers  (2020-12-26T15:21:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.