Conditional

By C. Fehringer. 2019

. In the context of sensitivity analysis of complex phenomena in presence of uncertainty, 4 we motivate and precise the idea of orienting the analysis towards a critical domain of the studied 5 phenomenon. For this, target and conditional sensitivity analyses are deﬁned. We make a brief 6 history of related approaches in the literature, and propose a more general and systematic approach. 7 Nonparametric measures of dependence being well-suited to this approach, we also make a review of 8 available methods and of their use for sensitivity analysis, and clarify some of their properties. Then, 9 we focus our attention on sensitivity indices based on correlation ratio, namely Sobol’ indices, and 10 on two dependence measures: the kernel quadratic dependence measure also called Hilbert–Schmidt 11 independence criterion and the Csiszár divergence dependence measure. We propose adapted versions 12 of these tools for target and conditional analysis, by considering transformation of the output using 13 hard or smooth weight functions. Finally, we show on synthetic numerical experiments both the 14 interest of target and conditional sensitivity analysis, and the eﬃciency of the dependence measures. 15 We also illustrate the relevance of the proposed smooth versions for conditional estimators. 16

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Pre-Trained Models: Past, Present and Future (2021, neutral): “…Lee et al., 2015), object detection (Ren et al., 2016; Sermanet et al., 2014; Gidaris and Komodakis, 2015), image segmentation (Long et al., 2015; Zheng et al., 2015), image caption (Vinyals et al., 2015; Johnson et al., 2016), visual question answering (Antol et al., 2015; Gao et al., 2015;…”
Editable Neural Networks (2020, positive): “For each editor We also compare to alternative editor function inspired by Conditional Neural Processes (CNP) (Garnelo et al. (2018)) that we refer to as Editable+CNP .”
Non-Local Recurrent Network for Image Restoration (2018, unknown): “In addition to image restoration, feature correlations are widely exploited along with neural networks in many other areas, including graphical models [53, 4, 18], relational reasoning [33], machine translation [14, 42] and so on.”