Toggle Poster Visibility
Oral
Tue Jul 20 07:00 PM -- 07:20 PM (PDT)
ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training
[ Paper ]
Spotlight
Tue Jul 20 07:20 PM -- 07:25 PM (PDT)
Householder Sketch for Accurate and Accelerated Least-Mean-Squares Solvers
[ Paper ]
Spotlight
Tue Jul 20 07:25 PM -- 07:30 PM (PDT)
Accumulated Decoupled Learning with Gradient Staleness Mitigation for Convolutional Neural Networks
[ Paper ]
Spotlight
Tue Jul 20 07:30 PM -- 07:35 PM (PDT)
Training Graph Neural Networks with 1000 Layers
[ Paper ]
Spotlight
Tue Jul 20 07:35 PM -- 07:40 PM (PDT)
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed
[ Paper ]
Spotlight
Tue Jul 20 07:40 PM -- 07:45 PM (PDT)
Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity
[ Paper ]
Spotlight
Tue Jul 20 07:45 PM -- 07:50 PM (PDT)
Ditto: Fair and Robust Federated Learning Through Personalization
[ Paper ]