Rong Ge

The Case for Cross-Component Power Coordination on Power Bounded Systems

2016

Modern computer systems are increasingly bounded by the available or permissible power at multiple layers, ranging from a single chip to an entire data center. To cope with this reality, it is necessary to understand …

A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network

2021 · arXiv (Cornell University)

While over-parameterization is widely believed to be crucial for the success of optimization for the neural networks, most existing theories on over-parameterization do not fully explain the reason -- they either work in the Neural …

Provably Learning Diverse Features in Multi-View Data with Midpoint Mixup

2022 · arXiv (Cornell University)

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art …