26 citations · 53 across the 10 of their papers we have counts for
9 papers · 1 filter
Efficient Long-Horizon Learning for Learned Optimization
Xiaolong Huang, Benjamin Thérien, James Harrison +1
Learned optimization aims to improve upon hand-designed optimizers (e.g., Adam and Muon) by meta-learning small neural network optimizers over a distribution of tasks. While recent…
Robo-taxi Fleet Coordination at Scale via Reinforcement Learning
Luigi Tresca, Carolin Schmidt, James Harrison +4
Fleets of robo-taxis offering on-demand transportation services, commonly known as Autonomous Mobility-on-Demand (AMoD) systems, hold significant promise for societal benefits, suc…
Applications of fractional calculus in learned optimization
Teodor Alexandru Szente, James Harrison, Mihai Zanfir +1
Fractional gradient descent has been studied extensively, with a focus on its ability to extend traditional gradient descent methods by incorporating fractional-order derivatives.…
Offline Hierarchical Reinforcement Learning via Inverse Optimization
Carolin Schmidt, Daniele Gammelli, James Harrison +2
Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon plannin…
Universal Neural Functionals
Allan Zhou, Chelsea Finn, James Harrison
A challenging problem in many modern machine learning tasks is to process weight-space features, i.e., to transform or extract information from the weights and gradients of a neura…
VeLO: Training Versatile Learned Optimizers by Scaling Up
Luke Metz, James Harrison, C. Daniel Freeman +8
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers. In this work, we leverage the sam…