Search Results for author:
Found 4 papers, 0 papers with code
Graph Learning with Loss-Guided Training
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.
LSH Microbatches for Stochastic Gradients: Value in Rearrangement
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.
Self-Similar Epochs: Value in Arrangement
Optimization of machine learning models is commonly performed through stochastic gradient updates on randomly ordered training examples.
Bootstrapped Graph Diffusions: Exposing the Power of Nonlinearity
Classic methods capture the graph structure through some underlying diffusion process that propagates through the graph edges.
