1 citations · 1 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Automatic mixed precision for optimizing gained time with constrained loss mean-squared-error based on model partition to sequential sub-graphs
Shmulik Markovich-Golan, Daniel Ohayon, Itay Niv +1
Quantization is essential for Neural Network (NN) compression, reducing model size and computational demands by using lower bit-width data types, though aggressive reduction often…
cs.LG2020★ 1 cited
Feature Whitening via Gradient Transformation for Improved Convergence
Shmulik Markovich-Golan, Barak Battash, Amit Bleiweiss
Feature whitening is a known technique for speeding up training of DNN. Under certain assumptions, whitening the activations reduces the Fisher information matrix to a simple ident…