TAPAS is a novel adaptive sampling method for the softmax model. It uses a two pass sampling strategy where the examples used to approximate the gradient of the partition function are first sampled according to a squashed population distribution and then resampled adaptively using the context and current model. We describe an efficient distributed implementation of TAPAS. We show, on both synthetic data and a large real dataset, that TAPAS has low computational overhead and works well for minimizing the rank loss for multi-class classification problems with a very large label space.
@article{arxiv.1707.03073,
title = {TAPAS: Two-pass Approximate Adaptive Sampling for Softmax},
author = {Yu Bai and Sally Goldman and Li Zhang},
journal= {arXiv preprint arXiv:1707.03073},
year = {2017}
}