Quantum Alphatron: quantum advantage for learning with kernels and noise - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Quantum Année : 2023

Quantum Alphatron: quantum advantage for learning with kernels and noise

Siyi Yang
  • Fonction : Auteur
Naixu Guo
Patrick Rebentrost
  • Fonction : Auteur

Résumé

At the interface of machine learning and quantum computing, an important question is what distributions can be learned provably with optimal sample complexities and with quantum-accelerated time complexities. In the classical case, Klivans and Goel discussed the A l p h a t r o n , an algorithm to learn distributions related to kernelized regression, which they also applied to the learning of two-layer neural networks. In this work, we provide quantum versions of the Alphatron in the fault-tolerant setting. In a well-defined learning model, this quantum algorithm is able to provide a polynomial speedup for a large range of parameters of the underlying concept class. We discuss two types of speedups, one for evaluating the kernel matrix and one for evaluating the gradient in the stochastic gradient descent procedure. We also discuss the quantum advantage in the context of learning of two-layer neural networks. Our work contributes to the study of quantum learning with kernels and from samples.

Dates et versions

hal-04533774 , version 1 (05-04-2024)

Identifiants

Citer

Siyi Yang, Naixu Guo, Miklos Santha, Patrick Rebentrost. Quantum Alphatron: quantum advantage for learning with kernels and noise. Quantum, 2023, 7, pp.1174. ⟨10.22331/q-2023-11-08-1174⟩. ⟨hal-04533774⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More