An analytic theory of shallow networks dynamics for hinge loss classification*
From MaRDI portal
Publication:5020044
Recommendations
- Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*
- Mean field analysis of neural networks: a law of large numbers
- Wide neural networks of any depth evolve as linear models under gradient descent *
- Global convergence and geometric characterization of slow to fast weight evolution in neural network training for classifying linearly non-separable data
- Mean Field Analysis of Deep Neural Networks
Cites work
- A mean field view of the landscape of two-layer neural networks
- Comparing dynamics: deep neural networks versus glassy systems
- Disentangling feature and lazy training in deep neural networks
- Ginzburg-Landau vortices, Coulomb gases, and renormalized energies
- Scaling description of generalization with number of parameters in deep learning
- Statistical mechanical analysis of learning dynamics of two-layer perceptron with multiple output units
- The implicit bias of gradient descent on separable data
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(4)- scientific article; zbMATH DE number 5578317 (Why is no real title available?)
- Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*
- Phase diagram of initial condensation for two-layer neural networks
- Embedding principle: a hierarchical structure of loss landscape of deep neural networks
This page was built for publication: An analytic theory of shallow networks dynamics for hinge loss classification*
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5020044)
