no code implementations • 19 Nov 2022 • Lifu Wang, Tianyu Wang, Shengwei Yi, Bo Shen, Bo Hu, Xing Cao
We study the learning ability of linear recurrent neural networks with Gradient Descent.
no code implementations • NeurIPS 2021 • Lifu Wang, Bo Shen, Bo Hu, Xing Cao
In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$.
no code implementations • 10 Jun 2020 • Lifu Wang, Bo Shen, Ning Zhao, Zhiyuan Zhang
In this paper, we follow this line to study the topology (sub-level sets) of the loss landscape of deep ReLU neural networks with a skip connection and theoretically prove that the skip connection network inherits the good properties of the two-layer network and skip connections can help to control the connectedness of the sub-level sets, such that any local minima worse than the global minima of some two-layer ReLU network will be very ``shallow".
no code implementations • 14 Oct 2019 • Lifu Wang, Bo Shen, Ning Zhao
This may have a negative influence on the convergence of the algorithm.