1 citations · 1 across the 5 of their papers we have counts for
5 papers
Linear RNNs Provably Learn Linear Dynamic Systems
Lifu Wang, Tianyu Wang, Shengwei Yi +3
We study the learning ability of linear recurrent neural networks with Gradient Descent. We prove the first theoretical guarantee on linear RNNs to learn any stable linear dynamic…
On the Provable Generalization of Recurrent Neural Networks
Lifu Wang, Bo Shen, Bo Hu +1
Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that ove…
Is the Skip Connection Provable to Reform the Neural Network Loss Landscape?
Lifu Wang, Bo Shen, Ning Zhao +1
The residual network is now one of the most effective structures in deep learning, which utilizes the skip connections to ``guarantee" the performance will not get worse. However,…
Second-Order Convergence of Asynchronous Parallel Stochastic Gradient Descent: When Is the Linear Speedup Achieved?
Lifu Wang, Bo Shen, Ning Zhao
In machine learning, asynchronous parallel stochastic gradient descent (APSGD) is broadly used to speed up the training process through multi-workers. Meanwhile, the time delay of…
The asymptotic behaviors of self excitation information diffusion processes for a large number of individuals
Lifu Wang, Bo Shen
The dynamics of opinion is a complex and interesting process, especially for the systems with large number individuals. It is usually hard to describe the evolutionary features of…