Picture for Alind Khare

Alind Khare

DεpS: Delayed ε-Shrinking for Faster Once-For-All Training

Add code
Jul 08, 2024
Figure 1 for DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Figure 2 for DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Figure 3 for DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Figure 4 for DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Viaarxiv icon

SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads

Add code
Dec 27, 2023
Viaarxiv icon

ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation

Add code
Oct 24, 2023
Figure 1 for ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
Figure 2 for ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
Figure 3 for ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
Figure 4 for ABKD: Graph Neural Network Compression with Attention-Based Knowledge Distillation
Viaarxiv icon

Subgraph Stationary Hardware-Software Inference Co-Design

Add code
Jun 21, 2023
Viaarxiv icon

SuperFed: Weight Shared Federated Learning

Add code
Jan 26, 2023
Viaarxiv icon

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

Add code
Oct 28, 2022
Figure 1 for UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Figure 2 for UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Figure 3 for UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Figure 4 for UnfoldML: Cost-Aware and Uncertainty-Based Dynamic 2D Prediction for Multi-Stage Classification
Viaarxiv icon

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

Add code
Apr 26, 2021
Figure 1 for CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
Figure 2 for CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
Figure 3 for CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
Figure 4 for CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment
Viaarxiv icon

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

Add code
Aug 10, 2020
Figure 1 for HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
Figure 2 for HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
Figure 3 for HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
Figure 4 for HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units
Viaarxiv icon

A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs

Add code
Oct 25, 2019
Figure 1 for A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Figure 2 for A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Figure 3 for A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Figure 4 for A Simple Dynamic Learning Rate Tuning Algorithm For Automated Training of DNNs
Viaarxiv icon