Skip to content
conftrace_

training dynamics

155 papers

Explore in graph

Also known as

TD

Co-occurring keywords · papers mentioning both

neural network optimization (28) neural network (15) neural tangent kernel (15) stochastic gradient descent (15) gradient descent (13) language model (11) large language model (9) representation learning (9) convergence analysis (7) model scaling (6)

Papers

A Solvable High-Dimensional Model of GAN NeurIPS 2019 Gradient Descent Finds Global Minima of Deep Neural Networks ICML 2019 LCA: Loss Change Allocation for Neural Network Training NeurIPS 2019 Towards a Better Understanding and Regularization of GAN Training Dynamics UAI 2019 Comparing Dynamics: Deep Neural Networks versus Glassy Systems ICML 2018