arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.15136stat.MLcs.LG
收藏

基于贝叶斯神经网络的低预算仿真推断

Low-Budget Simulation-Based Inference with Bayesian Neural Networks

University of Liège(列日大学);MIT(麻省理工学院);IAIFI(人工智能与基本物理中心);Anthropic(Anthropic公司)

Arnaud Delaunoy, Maxence de la Brassinne Bonardeaux, Siddharth Mishra-Sharma, Gilles Louppe

AI总结:

针对数据匮乏时仿真推断易过拟合且不可靠的问题,提出在低预算仿真推断中使用贝叶斯神经网络以显式考虑计算不确定性,设计了专用先验,在极少量仿真下即可获得校准良好的后验。

摘要:

仿真推断方法在数据匮乏的情况下被证明是不准确的,即当训练仿真受限或代价高昂时。在这种情况下,推断网络特别容易过拟合,若在使用时不考虑因网络权重缺乏可辨识性而产生的计算不确定性,将导致不可靠的结果。为解决这一问题,我们提出在低预算仿真推断中使用贝叶斯神经网络,从而显式地考虑后验近似的计算不确定性。我们设计了一系列专为推断量身定制的贝叶斯神经网络先验,并表明它们在测试的基准上能产生校准良好的后验,即使仅有 $O(10)$ 次仿真可用时亦然。这为使用代价极高的模拟器进行可靠的仿真推断开辟了可能性,正如我们在宇宙学领域的一个单次仿真计算代价高昂的问题上所展示的那样。我们表明,贝叶斯神经网络仅需几百次仿真即可产生信息丰富且校准良好的后验估计。

英文摘要:

Simulation-based inference methods have been shown to be inaccurate in the data-poor regime, when training simulations are limited or expensive. Under these circumstances, the inference network is particularly prone to overfitting, and using it without accounting for the computational uncertainty arising from the lack of identifiability of the network weights can lead to unreliable results. To address this issue, we propose using Bayesian neural networks in low-budget simulation-based inference, thereby explicitly accounting for the computational uncertainty of the posterior approximation. We design a family of Bayesian neural network priors that are tailored for inference and show that they lead to well-calibrated posteriors on tested benchmarks, even when as few as $O(10)$ simulations are available. This opens up the possibility of performing reliable simulation-based inference using very expensive simulators, as we demonstrate on a problem from the field of cosmology where single simulations are computationally expensive. We show that Bayesian neural networks produce informative and well-calibrated posterior estimates with only a few hundred simulations.

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。

↑