2 papers
stat.ML2020
DebiNet: Debiasing Linear Models with Nonlinear Overparameterized Neural Networks
Shiyun Xu, Zhiqi Bu
Recent years have witnessed strong empirical performance of over-parameterized neural networks on various tasks and many advances in the theory, e.g. the universal approximation an…
cs.LG2020
A Dynamical View on Optimization Algorithms of Overparameterized Neural Networks
Zhiqi Bu, Shiyun Xu, Kan Chen
When equipped with efficient optimization algorithms, the over-parameterized neural networks have demonstrated high level of performance even though the loss function is non-convex…