BatchEnsemble提升模型不确定性估计，效率远超传统方法。
Evaluating Prediction Uncertainty Estimates from BatchEnsemble
- 用批量集成框架实现高效不确定性估计，兼容表格与时序任务。
- 在预测与不确定性评估上表现媲美深度集成，优于蒙特卡洛丢弃法。
- 新提出的GRUBE模型参数更少，训练推理更快，适合实际部署。
深度学习模型在不确定性估计方面存在挑战，现有方法或计算成本过高，或低估不确定性。本文研究了批量集成（BatchEnsemble）作为一种通用且可扩展的不确定性估计方法，适用于表格和时间序列任务。为拓展其在序列建模中的应用，提出新型批量集成GRU单元（GRUBE）。对比蒙特卡洛丢弃法与深度集成模型，结果表明：BatchEnsemble在不确定性估计性能上与深度集成相当，显著优于蒙特卡洛丢弃法；GRUBE在预测与不确定性估计上表现相似或更优。这些成果显示，相较于传统集成方法，BatchEnsemble与GRUBE在参数更少、训练与推理时间更短的前提下，实现了相近甚至更好的性能。
原文摘要 · Abstract (English)
Deep learning models struggle with uncertainty estimation. Many approaches are either computationally infeasible or underestimate uncertainty. We investigate \textit{BatchEnsemble} as a general and scalable method for uncertainty estimation across both tabular and time series tasks. To extend BatchEnsemble to sequential modeling, we introduce GRUBE, a novel BatchEnsemble GRU cell. We compare the BatchEnsemble to Monte Carlo dropout and deep ensemble models. Our results show that BatchEnsemble matches the uncertainty estimation performance of deep ensembles, and clearly outperforms Monte Carlo dropout. GRUBE achieves similar or better performance in both prediction and uncertainty estimation. These findings show that BatchEnsemble and GRUBE achieve similar performance with fewer parameters and reduced training and inference time compared to traditional ensembles.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。