28 citations · 47 across the 6 of their papers we have counts for
6 papers
Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
Congliang Chen, Li Shen, Fangyu Zou +1
Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting v…
A Note on Chern-Yamabe Problem
Simone Calamai, Fangyu Zou
We propose a flow to study the Chern-Yamabe problem and discuss the long time existence of the flow. In the balanced case we show that the Chern-Yamabe problem is the Euler-Lagrang…
A Sufficient Condition for Convergences of Adam and RMSProp
Fangyu Zou, Li Shen, Zequn Jie +2
Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex se…
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
Li Shen, Congliang Chen, Fangyu Zou +3
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam…
The complex Monge-Ampére equation on the complement of a divisor
Fangyu Zou
We consider the complex Monge-Ampére equation on complete Kähler manifolds with cusp singularity along a divisor when the right hand side has rather weak regularity. We proved…
The Three-body Force and the Tetraquark Interpretation of Light Scalar Mesons
Fang-Yong Zou, Xiao-Lin Chen, Wei-Zhen Deng
We study the possible tetraquark interpretation of light scalar meson states , , , within the framework of the non-relativistic potential model. The wave…