4 citations · 5 across the 2 of their papers we have counts for
3 papers
cs.LG2021★ 4 cited
Lifelong Learning with Sketched Structural Regularization
Haoran Li, Aditya Krishnan, Jingfeng Wu +3
Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithm…
cs.LG2020★ 1 cited
Direction Matters: On the Implicit Bias of Stochastic Gradient Descent with Moderate Learning Rate
Jingfeng Wu, Difan Zou, Vladimir Braverman +1
Understanding the algorithmic bias of \emph{stochastic gradient descent} (SGD) is one of the key challenges in modern machine learning and deep learning theory. Most of the existin…
cs.LG2019
On the Noisy Gradient Descent that Generalizes as SGD
Jingfeng Wu, Wenqing Hu, Haoyi Xiong +3
The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and t…