Statistical Learning
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
Outsourcing Training without Uploading Data via Efficient Collaborative Open-Source Sampling
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and cost-effective end device.
Supplementary Material for " Label-Imbalanced
Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error.
Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Classical methods, such as weighted cross-entropy, fail when training deep nets to the terminal phase of training (TPT), that is training beyond zero training error.
