4 citations · 12 across the 24 of their papers we have counts for
Showing 2023Show all
3 papers · 1 filter
cs.LG2023
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
Mingze Wang, Zeping Min, Lei Wu
In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the spec…
cs.LG2023★ 1 cited
A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent
Mingze Wang, Lei Wu
In this paper, we provide a theoretical study of noise geometry for minibatch stochastic gradient descent (SGD), a phenomenon where noise aligns favorably with the geometry of loca…
cs.LG2023
Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks
Mingze Wang, Chao Ma
The training process of ReLU neural networks often exhibits complicated nonlinear phenomena. The nonlinearity of models and non-convexity of loss pose significant challenges for th…