Self-consistent dynamical field theory of kernel evolution in wide neural networks
From MaRDI portal
Recommendations
- Wide neural networks of any depth evolve as linear models under gradient descent *
- Infinite-width limit of deep linear neural networks
- Disentangling feature and lazy training in deep neural networks
- Mean-field limits of trained weights in deep learning: a dynamical systems perspective
- Mean Field Analysis of Deep Neural Networks
Cites work
- A mean field view of the landscape of two-layer neural networks
- Cubic regularization of Newton method and its global performance
- Cugliandolo-Kurchan equations for dynamics of spin-glasses
- Deep learning
- Disentangling feature and lazy training in deep neural networks
- High-dimensional dynamics of generalization error in neural networks
- scientific article; zbMATH DE number 3438144 (Why is no real title available?)
- scientific article; zbMATH DE number 1409619 (Why is no real title available?)
- Optimization with momentum: dynamical, control-theoretic, and symplectic perspectives
- Out-of-equilibrium dynamical mean-field equations for the perceptron model
- Reaction models in stochastic field theory
- Statistical field theory for neural networks
- The effective noise of stochastic gradient descent
- Trainability and Accuracy of Artificial Neural Networks: An Interacting Particle System Approach
- Unified field theoretical approach to deep and recurrent neuronal networks
- Wide neural networks of any depth evolve as linear models under gradient descent *
This page was built for publication: Self-consistent dynamical field theory of kernel evolution in wide neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6611447)
