Advances in neural information processing systems 7

Cios, Krzysztof J.; Shields, Mark E.

doi:10.1016/s0925-2312(97)90018-7

Cited by 17 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, in many architectures the N → ∞ limit is also one in which the network is drawn from a Gaussian process (GP), where, e.g. N is the width a of a fully-connected network [39][40][41][42] or the number of channels in a CNN [43,44]. The existence of such NNGP limits is quite general [45][46][47], and allows for training with Bayesian inference [39,41].…”

Section: ∞-Nnqsmentioning

confidence: 99%

“…This ODE becomes linear and analytically solvable for a mean-squared-error loss (see the supplementary material for a review of the NTK). Similarly, in the infinite-N limit, networks are often drawn from Gaussian processes [39][40][41][42], in which case they may be trained with Bayesian inference via another deterministic constant kernel, the neural network Gaussian process (NNGP) kernel [39].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Infinite neural network quantum states: entanglement and training dynamics

Luo

Halverson

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

We study infinite limits of neural network quantum states (∞-NNQS), which exhibit representation power through ensemble statistics, and also tractable gradient descent dynamics. Ensemble averages of Renyi entropies are expressed in terms of neural network correlators, and architectures that exhibit volume-law entanglement are presented. The analytic calculations of entanglemententropy are tractable because the ensemble statistics are simplified in the Gaussian process limit. A general framework is developed for studying the gradient descent dynamics of neural network quantum states (NNQS), using a quantum state neural tangent kernel (QS-NTK). For ∞-NNQS the training dynamics is simplified, since the QS-NTK becomes deterministic and constant. An analytic solution is derived for quantum state supervised learning, which allows an ∞-NNQS to recover any target wavefunction. Numerical experiments on finite and infinite NNQS in the transverse field Ising model and Fermi Hubbard model demonstrate excellent agreement with theory. ∞-NNQS opens up new opportunities for studying entanglement and training dynamics in other physics applications, such as in finding ground states.

show abstract

Section: ∞-Nnqsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Infinite neural network quantum states: entanglement and training dynamics

Luo

Halverson

2023

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…The same argument is generally valid for ensemble learning: This approach yields possible gains only if the ensemble set's predictors are different. Cios and Shields (1997) stated that the generalization error of a weighted combination of predictors in an ensemble is equal to the average error of the individual predictors minus the "disagreement" among them, which we henceforth refer to as "diversity. "…”

Section: Ensemble For Time Series Forecastingmentioning

confidence: 99%

Making the whole greater than the sum of its parts: A literature review of ensemble methods for financial time series forecasting

Albuquerque

Peng

Silva

2022

Journal of Forecasting

View full text Add to dashboard Cite

This paper discusses the application of ensemble techniques for the prediction of time series, presenting an in‐depth review of the main techniques and algorithms used by the recent literature, with emphasis on the bootstrap aggregation (bagging) and boosting approaches. We also discuss the theoretical foundations of the ensemble‐based models, presenting measures of model stability and the main aggregation methods to combine the forecasts of the individual models, as well as recommendations for future developments for related research agendas.

show abstract

“…Gallant described one of the first perceptron-based connectionist models where each cell i computes a single activation u i , which may be input to other cells or be an output of the network (145). Ricks et al gave one of the earliest quantum neural network models based on implementation of quantum circuitry with gates whose weights are evolved through learning using quantum search as well as piecewise weight allocation (146). In each step, we have a density operator for the qubits representing the hidden states, which can can be extracted with any output ancilliaries using a partial trace operator and fed forward to the next layer of the neural network where the unitary transformations that encapsulate the action of perceptrons can be applied.…”

Section: Quantum Reinforcement Learning and Deep Learningmentioning

confidence: 99%

Linear, Bidirectional and Circular Controlled Quantum Teleportation and Quantum State Sharing using a Seven Qubit Genuinely Entangled State

Majumdar¹

2020

Preprint

View full text Add to dashboard Cite

Multipartite entanglement is a resource for application in disparate protocols, of computing, communication and cryptography. In this paper, generation, characterisation and application of a genuine genuinely entangled seven-qubit resource state is studied. Theoretical schemes for quantum teleportation of arbitrary one, two and three qubits states, bidirectional teleportation of arbitrary two qubit states and probabilistic circular controlled teleportation as well as three schemes for undertaking tripartite quantum state sharing are presented.

show abstract

Advances in neural information processing systems 7

Cited by 17 publications

References 0 publications

Infinite neural network quantum states: entanglement and training dynamics

Infinite neural network quantum states: entanglement and training dynamics

Making the whole greater than the sum of its parts: A literature review of ensemble methods for financial time series forecasting

Linear, Bidirectional and Circular Controlled Quantum Teleportation and Quantum State Sharing using a Seven Qubit Genuinely Entangled State

Contact Info

Product

Resources

About