An end-to-end trainable hybrid classical-quantum classifier

Chen, Samuel Yen-Chi; Huang, Chih-Min; Hsing, Chia-Wei; Kao, Ying-Jer

doi:10.1088/2632-2153/ac104d

Cited by 39 publications

(33 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, there already exist efficient encoding strategies that map MPS into quantum circuits [61][62][63]. Moreover, several proposals were recently developed in which MPS are harnessed for quantum machine learning tasks, for example as part of hybrid classical-quantum algorithms [64,65] or as classical pre-training methods [66,67]. Similar ideas can be applied to the QMPS architecture by mapping the trainable MPS to a parametrized quantum circuit, thus directly integrating the QMPS framework in quantum computations with NISQ devices.…”

Section: Discussion/outlookmentioning

confidence: 99%

Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks

Metz¹,

Bukov²

2022

Preprint

View full text Add to dashboard Cite

Quantum many-body control is a central milestone en route to harnessing quantum technologies. However, the exponential growth of the Hilbert space dimension with the number of qubits makes it challenging to classically simulate quantum many-body systems and consequently, to devise reliable and robust optimal control protocols. Here, we present a novel framework for efficiently controlling quantum many-body systems based on reinforcement learning (RL). We tackle the quantum control problem by leveraging matrix product states (i) for representing the many-body state and, (ii) as part of the trainable machine learning architecture for our RL agent. The framework is applied to prepare ground states of the quantum Ising chain, including critical states. It allows us to control systems far larger than neural-network-only architectures permit, while retaining the advantages of deep learning algorithms, such as generalizability and trainable robustness to noise. In particular, we demonstrate that RL agents are capable of finding universal controls, of learning how to optimally steer previously unseen many-body states, and of adapting control protocols on-the-fly when the quantum dynamics is subject to stochastic perturbations.

show abstract

Section: Discussion/outlookmentioning

confidence: 99%

Self-Correcting Quantum Many-Body Control using Reinforcement Learning with Tensor Networks

Metz¹,

Bukov²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In the field of quantum machine learning (QML), applications of VQCs to standard machine learning tasks have achieved various degrees of success. Prominent examples include function approximation [13,[43][44][45], classification [13,14,[46][47][48][49][50][51][52][53][54][55][56][57][58][59][60][61][62][63], generative modeling [64][65][66][67][68], deep RL [29][30][31][32][33][69][70][71][72], sequence modeling [43,[73][74][75][76], speech recognition [77], metric and embedding learning [78,79], transfer learning [50,80] and federated learning [...…”

Section: Variational Quantum Circuitsmentioning

confidence: 99%

“…On the other hand, in [55], the authors explored the possibilities of using a TN for feature extraction and training the TN-VQC hybrid model in an end-to-end fashion. It has been shown that this hybrid TN-VQC architecture succeeds in classification tasks.…”

Section: Hybrid Tn-vqc Architecture For the Minigrid Problemmentioning

confidence: 99%

Variational quantum reinforcement learning via evolutionary optimization

Chen

Huang

Hsing

et al. 2022

Mach. Learn.: Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Recent advance in classical reinforcement learning (RL) and quantum computation (QC) points to a promising direction of performing RL on a quantum computer. However, potential applications in quantum RL are limited by the number of qubits available in modern quantum devices. Here we present two frameworks of deep quantum RL tasks using a gradient-free evolution optimization: First, we apply the amplitude encoding scheme to the Cart-Pole problem, where we demonstrate the quantum advantage of parameter saving using the amplitude encoding; Second, we propose a hybrid framework where the quantum RL agents are equipped with a hybrid tensor network-variational quantum circuit (TN-VQC) architecture to handle inputs of dimensions exceeding the number of qubits. This allows us to perform quantum RL on the MiniGrid environment with 147-dimensional inputs. The hybrid TN-VQC architecture provides a natural way to perform efficient compression of the input dimension, enabling further quantum RL applications on noisy intermediate-scale quantum devices.

show abstract

“…For a variational quantum eigensolver [24] or QAOA, the observable may be chosen as a non-local Hamiltonian encoding the problem that involves many qubit-qubit interactions. For machine learning tasks (e.g., classification), the observable can be defined locally on a few qubits whose states indicate the candidate output [25]. Later we will see that the choice of observables affects the landscape geometry.…”

Section: Variational Quantum Algorithmsmentioning

confidence: 99%