Kun Wu

On Batch Adaptive Training for Deep Learning: Lower Loss and Larger Step Size

2018

Mini-batch gradient descent and its variants are commonly used in deep learning. The principle of mini-batch gradient descent is to use noisy gradient calculated on a batch to estimate the real gradient, thus balancing the …

Towards Fair and Robust Classification

2022

Robustness and fairness are two equally important issues for machine learning systems. Despite the active research on robustness and fairness of ML recently, these efforts focus on either fairness or robustness, but not both. To …