Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits

• URL: http://arxiv.org/abs/2309.12681v2
• Date: Thu, 15 Feb 2024 20:14:33 GMT
• Title: Tight and Efficient Gradient Bounds for Parameterized Quantum Circuits
• Authors: Alistair Letcher, Stefan Woerner, Christa Zoufal
• Abstract summary: Training a parameterized model largely depends on the landscape of the underlying loss function. We show that these bounds, as well as the variance of the loss itself, can be estimated efficiently and classically-versa--providing practical tools to study the loss landscapes of VQA models. This insight has direct implications for hybrid Quantum Generative Adrial Networks (qGANs), a generative model that can be reformulated as a VQA with an observable composed of local and global terms.
• Score: 7.0379869298557844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The training of a parameterized model largely depends on the landscape of the underlying loss function. In particular, vanishing gradients (also known as barren plateaus) are a central bottleneck in the scalability of variational quantum algorithms (VQAs), and are known to arise in various ways, from circuit depth and hardware noise to global observables. However, a caveat of most existing gradient bound results is the requirement of t-design circuit assumptions that are typically not satisfied in practice. In this work, we loosen these assumptions altogether and derive tight upper and lower bounds on loss and gradient concentration for a large class of parameterized quantum circuits and arbitrary observables, which are significantly stronger than prior work. Moreover, we show that these bounds, as well as the variance of the loss itself, can be estimated efficiently and classically--providing practical tools to study the loss landscapes of VQA models, including verifying whether or not a circuit/observable induces barren plateaus. This insight has direct implications for hybrid Quantum Generative Adversarial Networks (qGANs), a generative model that can be reformulated as a VQA with an observable composed of local and global terms. We prove that designing the discriminator appropriately leads to 1-local weights that stay constant in the number of qubits, regardless of discriminator depth. Combined with our first contribution, this implies that qGANs with shallow generators can be trained at scale without suffering from barren plateaus, making them a promising candidate for applications in generative quantum machine learning. We demonstrate this result by training a qGAN to learn a 2D mixture of Gaussian distributions with up to 16 qubits, and provide numerical evidence that global contributions to the gradient may kick in substantially over the course of training.

Related papers

• Characterizing randomness in parameterized quantum circuits through expressibility and average entanglement [39.58317527488534]
  Quantum Circuits (PQCs) are still not fully understood outside the scope of their principal application. We analyse the generation of random states in PQCs under restrictions on the qubits connectivities. We place a connection between how steep is the increase on the uniformity of the distribution of the generated states and the generation of entanglement.
  arXiv  Detail & Related papers  (2024-05-03T17:32:55Z)
• Improving Parameter Training for VQEs by Sequential Hamiltonian Assembly [4.646930308096446]
  A central challenge in quantum machine learning is the design and training of parameterized quantum circuits (PQCs) We propose a Sequential Hamiltonian Assembly, which iteratively approximates the loss function using local components. Our approach outperforms conventional parameter training by 29.99% and the empirical state of the art, Layerwise Learning, by 5.12% in the mean accuracy.
  arXiv  Detail & Related papers  (2023-12-09T11:47:32Z)
• Gaussian initializations help deep variational quantum circuits escape from the barren plateau [87.04438831673063]
  Variational quantum circuits have been widely employed in quantum simulation and quantum machine learning in recent years. However, quantum circuits with random structures have poor trainability due to the exponentially vanishing gradient with respect to the circuit depth and the qubit number. This result leads to a general belief that deep quantum circuits will not be feasible for practical tasks.
  arXiv  Detail & Related papers  (2022-03-17T15:06:40Z)
• Toward Trainability of Deep Quantum Neural Networks [87.04438831673063]
  Quantum Neural Networks (QNNs) with random structures have poor trainability due to the exponentially vanishing gradient as the circuit depth and the qubit number increase. We provide the first viable solution to the vanishing gradient problem for deep QNNs with theoretical guarantees.
  arXiv  Detail & Related papers  (2021-12-30T10:27:08Z)
• Preparing Renormalization Group Fixed Points on NISQ Hardware [0.0]
  We numerically and experimentally study the robust preparation of the ground state of the critical Ising model using circuits adapted from the work of Evenbly and White. The experimental implementation exhibits self-correction through renormalization seen in the convergence and stability of local observables. We also numerically test error mitigation by zero-noise extrapolation schemes specially adapted for renormalization circuits.
  arXiv  Detail & Related papers  (2021-09-20T18:35:11Z)
• 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)
• Quantum Generative Training Using R\'enyi Divergences [0.22559617939136506]
  Quantum neural networks (QNNs) are a framework for creating quantum algorithms. A major challenge in QNN development is a concentration of measure phenomenon known as a barren plateau. We show that an unbounded loss function can circumvent the existing no-go results.
  arXiv  Detail & Related papers  (2021-06-17T14:50:53Z)
• Entanglement Induced Barren Plateaus [2.8038382295783943]
  We argue that an excess in entanglement between the visible and hidden units in a Quantum Neural Network can hinder learning. We show that quantum neural networks that satisfy a volume-law in the entanglement entropy will give rise to models not suitable for learning with high probability.
  arXiv  Detail & Related papers  (2020-10-29T22:05:30Z)
• A Statistical Framework for Low-bitwidth Training of Deep Neural Networks [70.77754244060384]
  Fully quantized training (FQT) uses low-bitwidth hardware by quantizing the activations, weights, and gradients of a neural network model. One major challenge with FQT is the lack of theoretical understanding, in particular of how gradient quantization impacts convergence properties.
  arXiv  Detail & Related papers  (2020-10-27T13:57:33Z)
• Characterizing the loss landscape of variational quantum circuits [77.34726150561087]
  We introduce a way to compute the Hessian of the loss function of VQCs. We show how this information can be interpreted and compared to classical neural networks.
  arXiv  Detail & Related papers  (2020-08-06T17:48:12Z)
• Efficient simulatability of continuous-variable circuits with large Wigner negativity [62.997667081978825]
  Wigner negativity is known to be a necessary resource for computational advantage in several quantum-computing architectures. We identify vast families of circuits that display large, possibly unbounded, Wigner negativity, and yet are classically efficiently simulatable. We derive our results by establishing a link between the simulatability of high-dimensional discrete-variable quantum circuits and bosonic codes.
  arXiv  Detail & Related papers  (2020-05-25T11:03:42Z)

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.