Chaos and Complexity from Quantum Neural Network: A study with Diffusion Metric in Machine Learning
November 16, 2020 Β· Declared Dead Β· π Journal of High Energy Physics
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Sayantan Choudhury, Ankan Dutta, Debisree Ray
arXiv ID
2011.07145
Category
hep-th
Cross-listed
cond-mat.dis-nn,
cs.LG,
nlin.CD,
quant-ph
Citations
22
Venue
Journal of High Energy Physics
Last Checked
3 months ago
Abstract
In this work, our prime objective is to study the phenomena of quantum chaos and complexity in the machine learning dynamics of Quantum Neural Network (QNN). A Parameterized Quantum Circuits (PQCs) in the hybrid quantum-classical framework is introduced as a universal function approximator to perform optimization with Stochastic Gradient Descent (SGD). We employ a statistical and differential geometric approach to study the learning theory of QNN. The evolution of parametrized unitary operators is correlated with the trajectory of parameters in the Diffusion metric. We establish the parametrized version of Quantum Complexity and Quantum Chaos in terms of physically relevant quantities, which are not only essential in determining the stability, but also essential in providing a very significant lower bound to the generalization capability of QNN. We explicitly prove that when the system executes limit cycles or oscillations in the phase space, the generalization capability of QNN is maximized. Finally, we have determined the generalization capability bound on the variance of parameters of the QNN in a steady state condition using Cauchy Schwartz Inequality.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β hep-th
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Searching the Landscape of Flux Vacua with Genetic Algorithms
R.I.P.
π»
Ghosted
Quantum stabilizer codes, lattices, and CFTs
R.I.P.
π»
Ghosted
Comments on the holographic description of Narain theories
R.I.P.
π»
Ghosted
Machine Learned Calabi-Yau Metrics and Curvature
R.I.P.
π»
Ghosted
Machine Learning Lie Structures & Applications to Physics
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted