Picture for Shiqi He

Shiqi He

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

Add code
Mar 27, 2023
Viaarxiv icon

GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning

Add code
Dec 03, 2022
Viaarxiv icon

Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions

Add code
Oct 11, 2022
Figure 1 for Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Figure 2 for Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Figure 3 for Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Figure 4 for Augmenting Operations Research with Auto-Formulation of Optimization Models from Problem Descriptions
Viaarxiv icon

Accelerating Federated Learning via Sampling Anchor Clients with Large Batches

Add code
Jun 13, 2022
Figure 1 for Accelerating Federated Learning via Sampling Anchor Clients with Large Batches
Figure 2 for Accelerating Federated Learning via Sampling Anchor Clients with Large Batches
Figure 3 for Accelerating Federated Learning via Sampling Anchor Clients with Large Batches
Figure 4 for Accelerating Federated Learning via Sampling Anchor Clients with Large Batches
Viaarxiv icon

Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression

Add code
Apr 14, 2022
Figure 1 for Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Figure 2 for Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Figure 3 for Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Figure 4 for Sign Bit is Enough: A Learning Synchronization Framework for Multi-hop All-reduce with Ultimate Compression
Viaarxiv icon