activity
20182023
most citedDynamic Space-Time Scheduling for GPU Inference

27 citations · 41 across the 9 of their papers we have counts for

collaborators

10 papers

cs.LG2022

UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification

Yanbo Xu, Alind Khare, Glenn Matlin +4

Machine Learning (ML) research has focused on maximizing the accuracy of predictive tasks. ML models, however, are increasingly more complex, resource intensive, and costlier to de…

cs.DC20221 cited

Automatic Parallelization of Python Programs for Distributed Heterogeneous Computing

Jun Shirako, Akihiro Hayashi, Sri Raj Paul +2

This paper introduces a novel approach to automatic ahead-of-time (AOT) parallelization and optimization of sequential Python programs for execution on distributed heterogeneous pl…

cs.CV20213 cited

CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment

Manas Sahni, Shreya Varshini, Alind Khare +1

The emergence of CNNs in mainstream deployment has necessitated methods to design and train efficient architectures tailored to maximize the accuracy under diverse hardware & laten…

cs.LG20204 cited

HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units

Shenda Hong, Yanbo Xu, Alind Khare +5

Deep learning models have achieved expert-level performance in healthcare with an exclusive focus on training accurate models. However, in many clinical environments such as intens…

cs.DC20201 cited

HyperSched: Dynamic Resource Reallocation for Model Development on a Deadline

Richard Liaw, Romil Bhardwaj, Lisa Dunlap +4

Prior research in resource scheduling for machine learning training workloads has largely focused on minimizing job completion times. Commonly, these model training workloads colle…

cs.DC2020

Cloudburst: Stateful Functions-as-a-Service

Vikram Sreekanti, Chenggang Wu, Xiayue Charles Lin +5

Function-as-a-Service (FaaS) platforms and "serverless" cloud computing are becoming increasingly popular. Current FaaS offerings are targeted at stateless functions that do minima…