no code implementations • 31 May 2020 • Eliav Buchnik, Edith Cohen
Classically, ML models trained with stochastic gradient descent (SGD) are designed to minimize the average loss per example and use a distribution of training examples that remains {\em static} in the course of training.
no code implementations • ICLR 2019 • Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias
We make a principled argument for the properties of our arrangements that accelerate the training and present efficient algorithms to generate microbatches that respect the marginal distribution of training examples.
no code implementations • ICLR 2019 • Eliav Buchnik, Edith Cohen, Avinatan Hassidim, Yossi Matias
Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples.
no code implementations • 7 Mar 2017 • Eliav Buchnik, Edith Cohen
Classic methods capture the graph structure through some underlying diffusion process that propagates through the graph edges.