James Lucas

Lookahead Optimizer: k steps forward, 1 step back

Michael R. Zhang, James Lucas, Geoffrey E. Hinton et al. · arXiv (Cornell University) · 2019 · 381 citations · Full text

Mathematical Programming, Structured Prediction, Large-scale Global Optimization +18

Lookahead Optimizer: k steps forward, 1 step back

Michael R. Zhang, James Lucas, Jimmy Ba et al. · Neural Information Processing Systems · 2019 · 175 citations

Mathematical Programming, Structured Prediction, Large-scale Global Optimization +17

Understanding Posterior Collapse in Generative Latent Variable Models

James Lucas, George Tucker, Roger Grosse et al. · International Conference on Learning Representations · 2019 · 78 citations

Latent Modeling, Engineering, Posterior Collapse +5

Preventing Gradient Attenuation in Lipschitz Constrained Convolutional Networks

Qiyang Li, Saminul Haque, Cem Anil et al. · arXiv (Cornell University) · 2019 · 33 citations · Full text

Artificial Intelligence, Geometric Learning, Convolutional Neural Network +13

Sorting out Lipschitz function approximation

Cem Anil, James Lucas, Roger Grosse · arXiv (Cornell University) · 2018 · 31 citations · Full text

Numerical Analysis, Artificial Intelligence, Engineering +17