arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.13624stat.MLcs.LGstat.ME
收藏

基于平衡神经比率估计的可靠仿真推理

Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation

University of Liège(列日大学)

Arnaud Delaunoy, Joeri Hermans, François Rozet, Antoine Wehenkel, Gilles Louppe

摘要:

基于模拟的现代推理方法依赖于深度学习代理,以实现计算机模拟器的近似推理。然而,在实践中,估计后验子的计算忠实性很少得到保证。例如,Hermans等人(2021)表明,当前基于模拟的推理算法可以产生过度自信的后验,因此有可能导致错误的推理。在这项工作中,我们介绍了平衡神经比率估计(BNRE),NRE算法的一种变体,旨在产生更保守的后验近似,从而提高其可靠性,同时共享相同的贝叶斯最优解。我们实现这一点,通过强制执行一个平衡条件,增加了量化的不确定性,在小的模拟预算制度,同时仍然收敛到确切的后验作为预算的增加。我们提供的理论论据表明,BNRE往往产生后代更保守的比NRE的。我们评估BNRE在各种各样的任务,并表明它产生保守的后验代理人在所有测试的基准和模拟预算。最后,我们强调,BNRE是直接实现NRE,不引入任何计算开销。

英文摘要:

Modern approaches for simulation-based inference rely upon deep learning surrogates to enable approximate inference with computer simulators. In practice, the estimated posteriors' computational faithfulness is, however, rarely guaranteed. For example, Hermans et al. (2021) show that current simulation-based inference algorithms can produce posteriors that are overconfident, hence risking false inferences. In this work, we introduce Balanced Neural Ratio Estimation (BNRE), a variation of the NRE algorithm designed to produce posterior approximations that tend to be more conservative, hence improving their reliability, while sharing the same Bayes optimal solution. We achieve this by enforcing a balancing condition that increases the quantified uncertainty in small simulation budget regimes while still converging to the exact posterior as the budget increases. We provide theoretical arguments showing that BNRE tends to produce posterior surrogates that are more conservative than NRE's. We evaluate BNRE on a wide variety of tasks and show that it produces conservative posterior surrogates on all tested benchmarks and simulation budgets. Finally, we emphasize that BNRE is straightforward to implement over NRE and does not introduce any computational overhead.

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。

↑