Grad Queue : A probabilistic framework to reinforce sparse gradients

arXiv:2404.16917v1 Announce Type: new
Abstract: Informative gradients are often lost in large batch updates. We propose a robust mechanism to reinforce the sparse components within a random batch of data points. A finite queue of online gradients is used to determine their expected instantaneous statistics. We propose a function to measure the scarcity of incoming gradients using these statistics and establish the theoretical ground of this mechanism. To minimize conflicting components within large mini-batches, samples are grouped with aligned objectives …

abstract arxiv components cs.ai cs.cv cs.lg data framework function lost queue random reinforce robust statistics type updates