Skip to content
conftrace_

momentum gradient descent

2 papers

Explore in graph

Also known as

MGD

Co-occurring keywords · papers mentioning both

implicit regularization (2) sparse solution (2) continuous-time analysis (1) diagonal linear network (1) overparameterized regression (1) overparametrized model (1) deep linear neural network (1) implicit regularisation (1) deep linear network (1) overparameterized model (1)

Papers

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks AISTATS 2024 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023