Corpus ID: 220424468

Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets

@article{Sharma2020ReformulationOT,
  title={Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets},
  author={Kunal Sharma and M. Cerezo and Z. Holmes and L. Cincio and A. Sornborger and Patrick J. Coles},
  journal={ArXiv},
  year={2020},
  volume={abs/2007.04900}
}
The No-Free-Lunch (NFL) theorem is a celebrated result in learning theory that limits one's ability to learn a function with a training data set. With the recent rise of quantum machine learning, it is natural to ask whether there is a quantum analog of the NFL theorem, which would restrict a quantum computer's ability to learn a unitary process (the quantum analog of a function) with quantum training data. However, in the quantum setting, the training data can possess entanglement, a strong… Expand
Barren Plateaus Preclude Learning Scramblers.
Absence of Barren Plateaus in Quantum Convolutional Neural Networks
Variational Quantum Algorithms
Connecting ansatz expressibility to gradient magnitudes and barren plateaus
Automated Machine Learning using Evolutionary Algorithms
  • M. Anton
  • Computer Science
  • 2020 IEEE 16th International Conference on Intelligent Computer Communication and Processing (ICCP)
  • 2020
Universal compiling and (No-)Free-Lunch theorems for continuous variable quantum learning
...
1
2
...

References

SHOWING 1-10 OF 65 REFERENCES
No Free Lunch for Quantum Machine Learning
Entanglement-assisted guessing of complementary measurement outcomes
Variational quantum state diagonalization
Hybrid quantum-classical approach to correlated materials
Quantum assisted quantum compiling
The quest for a Quantum Neural Network
General teleportation channel, singlet fraction and quasi-distillation
Barren plateaus in quantum neural network training landscapes
Trainability of Dissipative Perceptron-Based Quantum Neural Networks
...
1
2
3
4
5
...