Bayesian inference allows machine learning models to express uncertainty. Current machine learning models use only a single learnable parameter combination when making predictions, and as a result are highly overconfident when their predictions are wrong. To use more learnable parameter combinations efficiently, these samples must be drawn from the posterior distribution. Unfortunately computing the posterior directly is infeasible, so often researchers approximate it with a well known distribution such as a Gaussian. In this paper, we show that through the use of high-capacity persistent storage, models whose posterior distribution was too big to approximate are now feasible, leading to improved predictions in downstream tasks.
翻译:Bayesian 推论允许机器学习模型表达不确定性。 当前机器学习模型在作出预测时只使用单一的可学习参数组合,因此在预测错误时高度自信。 要高效地使用更多可学习参数组合,这些样本必须从后方分布中提取。 不幸的是,直接计算后方是行不通的, 研究人员通常会把它与众所周知的分布相近, 如高山。 在本文中,我们显示,通过使用高容量的持久性储存,其后方分布太大到无法估计的模型现在可以改进下游任务的预测。