论文标题
非挥发记忆加速后估计
Non-Volatile Memory Accelerated Posterior Estimation
论文作者
论文摘要
贝叶斯推论允许机器学习模型表达不确定性。当前的机器学习模型在做出预测时仅使用单个可学习的参数组合，因此，当他们的预测错误时，高度过度自信。要有效地使用更多可学习的参数组合，必须从后分布中绘制这些样本。不幸的是，直接计算后验是不可行的，因此研究人员经常会以众所周知的分布（例如高斯人）进行近似。在本文中，我们表明，通过使用大容量持久存储，后验分布太大而无法近似的模型现在是可行的，从而改善了下游任务的预测。
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.
