Quantum machine learning beyond kernel methods

Jerbi, Sofiène; Fiderer, Lukas J.; Nautrup, Hendrik Poulsen; Kübler, Jonas M.; Briegel, Hans J.; Dunjko, Vedran

doi:10.1038/s41467-023-36159-y

Cited by 69 publications

(38 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The QGAIL with amplitude encoding has a logarithmic scaling but there is no known efficient algorithm to encode the arbitrary classical data into the quantum memory in a superposition way [51]. The parameter complexity advantage in VQC-based supervised learning is also empirically observed in [52][53][54][55]. These quantum algorithms demonstrates the parameter complexity advantage of VQC in QML for classical tasks.…”

Section: Qgail For Quantum Controlmentioning

confidence: 94%

Quantum generative adversarial imitation learning

Xiao

Huang²,

Li³

et al. 2023

New J. Phys.

View full text Add to dashboard Cite

Investigating quantum advantage in the NISQ era is a challenging problem whereas quantum machine learning becomes the most promising application that can be resorted to. However, no proposal has been investigated for arguably challenging inverse reinforcement learning to demonstrate the potential advantage. In this work, we propose a hybrid quantum-classical inverse reinforcement learning algorithm based on the variational quantum circuit with the generative adversarial framework. We find an important connection between the quantum gradient anomaly and the performance degradation, which suggest a gradient clipping strategy to stabilize the training process. In light of the algorithm, we study three classic control problems and the Hamiltonian parameter estimation in quantum sensing with shallow quantum circuits. The numerical results showcase that the control-enhanced quantum sensor can saturate quantum Cram'er-Rao bound only with a single variational layer, empirically demonstrating a parameter complexity advantage over the classical learning control. The proposed generative adversarial reinforcement learning algorithm achieves state-of-the-art performance in classical and quantum sensor control in terms of required number of parameters.

show abstract

Section: Qgail For Quantum Controlmentioning

confidence: 94%

Quantum generative adversarial imitation learning

Xiao

Huang²,

Li³

et al. 2023

New J. Phys.

View full text Add to dashboard Cite

show abstract

“…Like other quantum machine learning models (Lloyd et al, 2020;Jerbi et al, 2021), QNLP models encode words to different qubits, and design the quantum circuit routine (a.k.a ansatz) to derive the sentence representation before feeding it to a measurement layer. In its mathematical form, the model encodes each word to a unit complex vector and it has an all-linear structure up to the measurement outcome.…”

Section: Complex-valued Neural Networkmentioning

confidence: 99%

Identity of university Chinese heritage language learners in Hong Kong

Li¹,

李蓁²

View full text Add to dashboard Cite

The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn shortcuts instead of comprehensive representations. In this work, we find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We deeply explore the main contributors of OOD detection and find that reconstructionbased pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset. Specifically, we take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD). Without bells and whistles, MOOD outperforms previous SOTA of one-class OOD detection by 5.7%, multi-class OOD detection by 3.0%, and near-distribution OOD detection by 2.1%. It even defeats the 10-shot-per-class outlier exposure OOD detection, although we do not include any OOD samples for our detection.

show abstract

“…However, due to this quantum feature mapping, the interpretation of the vector quantization algorithm with respect to the original data space may be limited, whereas, within the Bloch sphere (Hilbert space), the prototype principle and interpretation paradigms remain true. Thereby, the mapping here is analogous to the kernel feature mapping in support vector machines [ 38 ] as pointed out frequently [ 85 , 86 , 87 ].…”

Section: Quantum Approaches For Vector Quantizationmentioning

confidence: 99%

Quantum Computing Approaches for Vector Quantization—Current Perspectives and Developments

Engelsberger

Villmann

2023

Entropy

View full text Add to dashboard Cite

In the field of machine learning, vector quantization is a category of low-complexity approaches that are nonetheless powerful for data representation and clustering or classification tasks. Vector quantization is based on the idea of representing a data or a class distribution using a small set of prototypes, and hence, it belongs to interpretable models in machine learning. Further, the low complexity of vector quantizers makes them interesting for the application of quantum concepts for their implementation. This is especially true for current and upcoming generations of quantum devices, which only allow the execution of simple and restricted algorithms. Motivated by different adaptation and optimization paradigms for vector quantizers, we provide an overview of respective existing quantum algorithms and routines to realize vector quantization concepts, maybe only partially, on quantum devices. Thus, the reader can infer the current state-of-the-art when considering quantum computing approaches for vector quantization.

show abstract

Quantum machine learning beyond kernel methods

Cited by 69 publications

References 37 publications

Quantum generative adversarial imitation learning

Quantum generative adversarial imitation learning

Identity of university Chinese heritage language learners in Hong Kong

Quantum Computing Approaches for Vector Quantization—Current Perspectives and Developments

Contact Info

Product

Resources

About