78 citations · 121 across the 12 of their papers we have counts for
12 papers
Hidden symmetries of ReLU networks
J. Elisenda Grigsby, Kathryn Lindsey, David Rolnick
The parameter space for any fixed architecture of feedforward ReLU neural networks serves as a proxy during training for the associated class of functions - but how faithful is thi…
PGrad: Learning Principal Gradients For Domain Generalization
Zhe Wang, Jake Grigsby, Yanjun Qi
Machine learning models fail to perform when facing out-of-distribution (OOD) domains, a challenging task known as domain generalization (DG). In this work, we develop a novel DG t…
Launchpad: Learning to Schedule Using Offline and Online RL Methods
Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw +1
Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes tho…
RARE: Renewable Energy Aware Resource Management in Datacenters
Vanamala Venkataswamy, Jake Grigsby, Andrew Grimshaw +1
The exponential growth in demand for digital services drives massive datacenter energy consumption and negative environmental impacts. Promoting sustainable solutions to pressing e…
Benchmarks for a Global Extraction of Information from Deeply Virtual Exclusive Scattering
Manal Almaeen, Jake Grigsby, Joshua Hoskins +4
We develop a framework to establish benchmarks for machine learning and deep neural networks analyses of exclusive scattering cross sections (FemtoNet). Within this framework we pr…
MetaCon: Unified Predictive Segments System with Trillion Concept Meta-Learning
Keqian Li, Yifan Hu, Logan Palanisamy +6
Accurate understanding of users in terms of predicative segments play an essential role in the day to day operation of modern internet enterprises. Nevertheless, there are signific…