Barren plateaus in quantum tensor network optimization

Martín, Enrique Cervero; Plekhanov, Kirill; Lubasch, Michael

doi:10.22331/q-2023-04-13-974

Cited by 21 publications

(3 citation statements)

References 81 publications

(156 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same approach may also reduce the amount of training data needed [40]. Furthermore, recent results suggest that generative hierarchical QTNs can mitigate the exponentially vanishing gradients as single qubit observables causally depend only on a logarithmic number of gates [101]. This coincides with findings using ZX-calculus that MPS and layered VQCs will experience barren plateaus, but hierarchical TNs will not as their variance does not vanish exponentially with the system size [100].…”

Section: (C) Variational Machine Learning With Quantum Tensor Networksupporting

confidence: 58%

“…In principle, any other layout than a MPS also can be embedded into the brickwall. As their QTN pendants are more efficiently trainable [101], this may result in further improvement over MPS. The pre-training approach can be seen as a quantum version of the copy node initialization for classical TNs, where most of the tensor nodes are initialized with identity tensors [49].…”

Section: (C) Variational Machine Learning With Quantum Tensor Networkmentioning

confidence: 99%

See 1 more Smart Citation

Tensor networks for quantum machine learning

2023

View full text Add to dashboard Cite

Once developed for quantum theory, tensor networks (TNs) have been established as a successful machine learning (ML) paradigm. Now, they have been ported back to the quantum realm in the emerging field of quantum ML to assess problems that classical computers are unable to solve efficiently. Their nature at the interface between physics and ML makes TNs easily deployable on quantum computers. In this review article, we shed light on one of the major architectures considered to be predestined for variational quantum ML. In particular, we discuss how layouts like matrix product state, projected entangled pair states, tree tensor networks and multi-scale entanglement renormalization ansatz can be mapped to a quantum computer, how they can be used for ML and data encoding and which implementation techniques improve their performance.

show abstract

Section: (C) Variational Machine Learning With Quantum Tensor Networksupporting

confidence: 58%

Section: (C) Variational Machine Learning With Quantum Tensor Networkmentioning

confidence: 99%

Tensor networks for quantum machine learning

2023

View full text Add to dashboard Cite

show abstract

“…This process determines probabilities for two possible outcomes, 𝑝 0 and 𝑝 1 by measuring the average state of the qubits, with each outcome directly mapping to a class label. The tree-like design of our introduced model species promotes not only efficient computation but also a natural resistance to the occurrence of barren plateaus during the training process, a notable hurdle in the optimization of quantum models [22][23][24].…”

Section: Resultsmentioning

confidence: 99%

Application of Quantum Tensor Networks for Protein Classification

Kundu,

Ghosh,

Ekambaram

et al. 2024

Preprint

View full text Add to dashboard Cite

Computational methods in drug discovery significantly reduce both time and experimental costs. Nonetheless, certain computational tasks in drug discovery can be daunting with classical computing techniques which can be potentially overcome using quantum computing. A crucial task within this domain involves the functional classification of proteins. However, a challenge lies in adequately representing lengthy protein sequences given the limited number of qubits available in existing noisy quantum computers. We show that protein sequences can be thought of as sentences in natural language processing and can be parsed using the existing Quantum Natural Language framework into parameterized quantum circuits of reasonable qubits, which can be trained to solve various proteinrelated machine-learning problems. We classify proteins based on their sub-cellular locations—a pivotal task in bioinformatics that is key to understanding biological processes and disease mechanisms. Leveraging the quantum-enhanced processing capabilities, we demonstrate that Quantum Tensor Networks (QTN) can effectively handle the complexity and diversity of protein sequences. We present a detailed methodology that adapts QTN architectures to the nuanced requirements of protein data, supported by comprehensive experimental results. We demonstrate two distinct QTNs, inspired by classical recurrent neural networks (RNN) and convolutional neural networks (CNN), to solve the binary classification task mentioned above. Our top-performing quantum model has achieved a 94% accuracy rate, which is comparable to the performance of a classical model that uses the ESM2 protein language model embeddings. It’s noteworthy that the ESM2 model is extremely large, containing 8 million parameters in its smallest configuration, whereas our best quantum model requires only around 800 parameters. We demonstrate that these hybrid models exhibit promising performance, showcasing their potential to compete with classical models of similar complexity.

show abstract

Variational quantum multidimensional scaling algorithm

Zhang,

Guo

et al. 2024

Quantum Inf Process

View full text Add to dashboard Cite

Barren plateaus in quantum tensor network optimization

Cited by 21 publications

References 81 publications

Tensor networks for quantum machine learning

Tensor networks for quantum machine learning

Application of Quantum Tensor Networks for Protein Classification

Variational quantum multidimensional scaling algorithm

Contact Info

Product

Resources

About