Diederik P. Kingma

Adam-mini: Use Fewer Learning Rates To Gain More

arXiv 2024

DeMo: Decoupled Momentum Optimization

arXiv 2024

Score-Based Generative Modeling through Stochastic Differential Equations

score-based-generative-modeling-through

Glow: Generative Flow with Invertible 1x1 Convolutions

glow-generative-flow-with-invertible-1x1-1

PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications

arXiv 2017

Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks

weight-normalization-a-simple-1

Tim Salimans

Abhishek Kumar

Andrej Karpathy

founder

Ben Poole

Bowen Peng

researcher

Chenwei Wu

Congliang Chen

Jascha Sohl-Dickstein

Jeffrey Quesnelle

founder

Prafulla Dhariwal