Search Results for author:
Found 2 papers, 1 papers with code
KrADagrad: Kronecker Approximation-Domination Gradient Preconditioned Stochastic Optimization
Second order stochastic optimizers allow parameter update step size and direction to adapt to loss curvature, but have traditionally required too much memory and compute for deep learning.
SKI to go Faster: Accelerating Toeplitz Neural Networks via Asymmetric Kernels
For the low rank component, we replace the RPE MLP with linear interpolation and use asymmetric Structured Kernel Interpolation (SKI) (Wilson et.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
