Recently, Neural Radiance Field (NeRF) has shown great success in render...
Stochastic gradients closely relate to both optimization and generalizat...
People usually believe that network pruning not only reduces the
computa...
The great success of deep learning heavily relies on increasingly larger...
It is well-known that the Hessian matters to optimization, generalizatio...
It is well-known that stochastic gradient noise (SGN) acts as implicit
r...
Weight decay is a popular regularization technique for training of deep
...
Deep learning is often criticized by two serious issues which rarely exi...
Adaptive Momentum Estimation (Adam), which combines Adaptive Learning Ra...
Stochastic optimization algorithms, such as Stochastic Gradient Descent ...