activity
20172023
most citedPort-Hamiltonian Neural Networks for Learning Explicit Time-Dependent Dynamical Systems

51 citations · 110 across the 18 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG20231 cited

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…

cs.LG2023

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…

cs.LG20221 cited

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…

cs.LG202151 cited

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…

cs.LG20213 cited

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…

cs.LG20213 cited

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…