Corpus ID: 208158021

Universality for Langevin-like spin glass dynamics

@article{Dembo2019UniversalityFL,
  title={Universality for Langevin-like spin glass dynamics},
  author={A. Dembo and Eyal Lubetzky and Ofer Zeitouni},
  journal={arXiv: Probability},
  year={2019}
}
We study dynamics for asymmetric spin glass models, proposed by Hertz et al. and Sompolinsky et al. in the 1980's in the context of neural networks: particles evolve via a modified Langevin dynamics for the Sherrington--Kirkpatrick model with soft spins, whereby the disorder is i.i.d. standard Gaussian rather than symmetric. Ben Arous and Guionnet (1995), followed by Guionnet (1997), proved for Gaussian interactions that as the number of particles grows, the short-term empirical law of this… Expand
1 Citations

Figures from this paper

Diffusions interacting through a random matrix: universality via stochastic Taylor expansion
  • 1
  • PDF

References

SHOWING 1-10 OF 35 REFERENCES
Large deviations for Langevin spin glass dynamics
  • 56
  • Highly Influential
  • PDF
Symmetric Langevin spin glass dynamics
  • 45
Dynamics of spin systems with randomly asymmetric bonds: Langevin dynamics and a spherical model.
  • 115
  • Highly Influential
  • PDF
Relaxational dynamics of the Edwards-Anderson model and the mean-field theory of spin-glasses
  • 267
Sanov results for Glauber spin-glass dynamics
  • 25
Large Deviations, Dynamics and Phase Transitions in Large Stochastic and Disordered Neural Networks
  • 28
  • PDF
The Thermodynamic Limit in Mean Field Spin Glass Models
  • 323
  • PDF
Irreversible spin glasses and neural networks
  • 26
...
1
2
3
4
...