1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. A Study Of Generalization Of Stochastic Mirror Descent Algorithms On Overparameterized Nonlinear Models

A Study Of Generalization Of Stochastic Mirror Descent Algorithms On Overparameterized Nonlinear Models

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

We study the convergence, the implicit regularization and the generalization of stochastic mirror descent (SMD) algorithms in overparameterized nonlinear models, where the number of model parameters exceeds the number of training data points. Due to overp

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

A Study Of Generalization Of Stochastic Mirror Descent Algorithms On Overparameterized Nonlinear Models

00:14:46

0 views

We study the convergence, the implicit regularization and the generalization of stochastic mirror descent (SMD) algorithms in overparameterized nonlinear models, where the number of model parameters exceeds the number of training data points. Due to overp