4 citations · 6 across the 2 of their papers we have counts for
2 papers
cs.CV2023★ 2 cited
StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation
Huizong Yang, Yuxin Sun, Ganesh Sundaramoorthi +1
We present new insights and a novel paradigm (StEik) for learning implicit neural representations (INR) of shapes. In particular, we shed light on the popular eikonal loss used for…
cs.LG2022★ 4 cited
A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks
Yuxin Sun, Dong Lao, Ganesh Sundaramoorthi +1
We discover restrained numerical instabilities in current training practices of deep networks with stochastic gradient descent (SGD), and its variants. We show numerical error (on…