80 citations · 197 across the 25 of their papers we have counts for
4 papers · 1 filter
Lyapunov Exponents for Diversity in Differentiable Games
Jonathan Lorraine, Paul Vicol, Jack Parker-Holder +3
Ridge Rider (RR) is an algorithm for finding diverse solutions to optimization problems by following eigenvectors of the Hessian ("ridges"). RR is designed for conservative gradien…
Input Convex Gradient Networks
Jack Richter-Powell, Jonathan Lorraine, Brandon Amos
The gradients of convex functions are expressive models of non-trivial vector fields. For example, Brenier's theorem yields that the optimal transport map between any two measures…
Meta-Learning to Improve Pre-Training
Aniruddh Raghu, Jonathan Lorraine, Simon Kornblith +2
Pre-training (PT) followed by fine-tuning (FT) is an effective method for training neural networks, and has led to significant performance improvements in many domains. PT can inco…
Complex Momentum for Optimization in Games
Jonathan Lorraine, David Acuna, Paul Vicol +1
We generalize gradient descent with momentum for optimization in differentiable games to have complex-valued momentum. We give theoretical motivation for our method by proving conv…