用并行采样加速贝叶斯深度学习，提升不确定性估计精度。
Scalable Bayesian Monte Carlo: fast uncertainty estimation beyond deep ensembles
- 通过插值点估计与后验分布构建新模型，结合并行采样算法。
- 同等耗时下，准确率相当，认知不确定性量化显著优于深度集成。
- 适合需要可靠置信度评估的实用场景，如模型拒答或可靠性判断。
本文提出一种名为可扩展贝叶斯蒙特卡洛（SBMC）的新方法，用于贝叶斯深度学习。该方法包含一个介于点估计器与后验分布之间的模型，以及一种并行实现的序列蒙特卡洛采样器（SMC$_\parallel$）或马尔可夫链蒙特卡洛（MCMC$_\parallel$）算法。我们统称这些一致（渐近无偏）算法为贝叶斯蒙特卡洛（BMC），SBMC可兼容任意此类算法。在MNIST、CIFAR和IMDb等实际任务上的实验表明：在与当前最优方法（如深度集成，DE）相同的运行时间内，SBMC在准确率上相当或更优，且显著提升了不确定性量化（UQ）能力，尤其在认知不确定性方面表现突出。该方法可用于下游任务中预测置信度估计，支持可靠性评估或拒绝预测决策。
原文摘要 · Abstract (English)
This work introduces a new method designed for Bayesian deep learning called scalable Bayesian Monte Carlo (SBMC). The method is comprised of a model and an algorithm. The model interpolates between a point estimator and the posterior. The algorithm is a parallel implementation of sequential Monte Carlo sampler (SMC$_\parallel$) or Markov chain Monte Carlo (MCMC$_\parallel$). We collectively refer to these consistent (asymptotically unbiased) algorithms as Bayesian Monte Carlo (BMC), and any such algorithm can be used in our SBMC method. The utility of the method is demonstrated on practical examples: MNIST, CIFAR, IMDb. A systematic numerical study reveals that for the same wall-clock time as state-of-the-art (SOTA) methods like deep ensembles (DE), SBMC achieves comparable or better accuracy and substantially improved uncertainty quantification (UQ)--in particular, epistemic UQ. This is demonstrated on the downstream task of estimating the confidence in predictions, which can be used for reliability assessment or abstention decisions.
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。