NP-PROV:方差仅与位置相关的神经过程
NP-PROV: Neural Processes with Position-Relevant-Only Variances
摘要:
神经过程(NP)家族将函数上的分布编码为潜在表示,给定上下文数据,并解码未知位置处的后验均值和方差。由于均值和方差来自相同的潜在空间,因此它们可能会在域外任务中失败,其中函数值的波动放大了模型的不确定性。我们提出了一个新的成员命名为神经过程与位置相关的唯一方差(NP-PROV)。NP-PROV假设靠近上下文点的目标点具有小的不确定性,而不管该位置处的函数值如何。由此产生的方法分别从函数值相关的空间和位置相关的潜在空间导出均值和方差。我们对合成数据集和真实数据集的评估表明,当函数值存在漂移时,NP-PROV可以实现最先进的似然性,同时保持有界方差。
英文摘要:
Neural Processes (NPs) families encode distributions over functions to a latent representation, given context data, and decode posterior mean and variance at unknown locations. Since mean and variance are derived from the same latent space, they may fail on out-of-domain tasks where fluctuations in function values amplify the model uncertainty. We present a new member named Neural Processes with Position-Relevant-Only Variances (NP-PROV). NP-PROV hypothesizes that a target point close to a context point has small uncertainty, regardless of the function value at that position. The resulting approach derives mean and variance from a function-value-related space and a position-related-only latent space separately. Our evaluation on synthetic and real-world datasets reveals that NP-PROV can achieve state-of-the-art likelihood while retaining a bounded variance when drifts exist in the function value.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。