51 citations · 110 across the 18 of their papers we have counts for
15 papers · 1 filter
The instabilities of large learning rate training: a loss landscape view
Lawrence Wang, Stephen Roberts
Modern neural networks are undeniably successful. Numerous works study how the curvature of loss landscapes can affect the quality of solutions. In this work we study the loss land…
SANE: The phases of gradient descent through Sharpness Adjusted Number of Effective parameters
Lawrence Wang, Stephen J. Roberts
Modern neural networks are undeniably successful. Numerous studies have investigated how the curvature of loss landscapes can affect the quality of solutions. In this work we consi…
Learning General World Models in a Handful of Reward-Free Deployments
Yingchen Xu, Jack Parker-Holder, Aldo Pacchiano +5
Building generally capable agents is a grand challenge for deep reinforcement learning (RL). To approach this challenge practically, we outline two key desiderata: 1) to facilitate…
Port-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems
Shaan Desai, Marios Mattheakis, David Sondak +2
Accurately learning the temporal behavior of dynamical systems requires models with well-chosen learning biases. Recent innovations embed the Hamiltonian and Lagrangian formalisms…
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL
Jack Parker-Holder, Vu Nguyen, Shaan Desai +1
Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field…
Can convolutional ResNets approximately preserve input distances? A frequency analysis perspective
Lewis Smith, Joost van Amersfoort, Haiwen Huang +2
ResNets constrained to be bi-Lipschitz, that is, approximately distance preserving, have been a crucial component of recently proposed techniques for deterministic uncertainty quan…