EXACT: How to Train Your Accuracy. (arXiv:2205.09615v2 [cs.LG] UPDATED)

Web: http://arxiv.org/abs/2205.09615

Classification tasks are usually evaluated in terms of accuracy. However,
accuracy is discontinuous and cannot be directly optimized using gradient
ascent. Popular methods minimize cross-entropy, Hinge loss, or other surrogate
losses, which can lead to suboptimal results. In this paper, we propose a new
optimization framework by introducing stochasticity to a model's output and
optimizing expected accuracy, i.e. accuracy of the stochastic model. Extensive
experiments on image classification show that the proposed optimization method
is a powerful alternative to widely …

accuracy arxiv lg