Toward a perception-based theory of probabilistic reasoning with imprecise probabilities

By Lotfi A. Zadeh. 2002

2,041 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Networks and Communications, Probabilistic & Bayesian Methods

How researchers see this paper

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

In Artificial Intelligence

In Computational Theory and Mathematics

In Computer Networks and Communications

In Probabilistic & Bayesian Methods

Citations in the corpus

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (2015, background): “When the input distribution to a learning system changes, it is said to experience covariate shift (Shimodaira, 2000).”
Root Mean Square Layer Normalization (2019, background): “d inputs, pRMSNorm achieves competitive performance compared to RMSNorm. 2 Related Work One bottleneck deep neural networks have been hypothesized to suffer from is the internal covariate shift issue [27], where a layer’s input distribution changes as previous layers are updated, which signiﬁcantly ”
Unsupervised Domain Adaptation by Backpropagation (2014, background): “Under the covariate shift assumption, this would make the label prediction accuracy on the target domain to be the same as on the source domain [18].”
Recurrent Batch Normalization (2016, background): “It is well-known that for deep feed-forward neural networks, covariate shift (Shimodaira, 2000; Ioffe & Szegedy, 2015) degrades the efﬁciency of training.”
Evaluating Models’ Local Decision Boundaries via Contrast Sets (2020, background): “, 2018), and covariate and label shifts (Ben-David et al., 2010; Shimodaira, 2000; Lipton et al., 2018).”
PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples (2017, background): “However, if their model is misspecified, the uncertainty estimates can be affected by covariate shift (Shimodaira, 2000).”
On the Safety of Machine Learning: Cyber-Physical Systems, Decision Sciences, and Data Products (2016, background): “Further, it may be that the distribution the samples actually come from cannot be known, precluding the use of covariate shift [14] and domain adaptation techniques [15].”
Data Augmentation Generative Adversarial Networks (2017, background): “The term dataset shift (Storkey, 2009) generalises the concept of covariate shift (Shimodaira, 2000; Storkey & Sugiyama, 2007; Sugiyama & Müller, 2005) to multiple cases of changes between domains.”
Weakly-Supervised Disentanglement Without Compromises (2020, background): “, 2017) under covariate shifts (Shimodaira, 2000; Quionero-Candela et al., 2009; Ben-David et al., 2010), fairer downstream predictions (Locatello et al.”
Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift (2018, background): “, 2010), these papers often assume either covariate shift q(x, y) = q(x)p(y|x) (Shimodaira, 2000; Sugiyama et al., 2008; Gretton et al., 2009) or label shift q(x, y) = q(y)p(x|y) (Saerens et al.”
Learning Robust Representations by Projecting Superficial Statistics Out (2018, background): “Under restrictive assumptions, such as covariate shift (Shimodaira, 2000; Gretton et al., 2009), and label shift (also known as target shift or prior probability shift ) (Storkey, 2009; Sch¨olkopf et al., 2012; Zhang et al., 2013; Lipton et al., 2018), principled methods exist for estimating the…”
Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms (2018, methodology): “These methods work by re-weighting the training data or extracting transferable features (e.g., Shimodaira (2000); Gretton et al. (2009); Gong et al. (2016); Zhang et al. (2013)).”
Detecting and Correcting for Label Shift with Black Box Predictors (2018, methodology): “Shimodaira (2000) proposed correcting models via weighting examples in ERM by q ( x ) /p ( x ) .”
Domain Adaptation with Conditional Transferable Components (2016, background): “In this case, one can match the feature distribution P (X) on source and target domains by importance reweighting methods if the source domain is richer than the target domain (Shimodaira, 2000; Sugiyama et al., 2008; Huang et al., 2007).”
Multi-Source Domain Adaptation: A Causal View (2015, methodology): “Previous work in domain adaptation has usually assumed that P X changes but P Y | X remain the same, i.e., the covariate shift situation; see, e.g., (Shimodaira 2000; Huang et al. 2007; Sugiyama et al. 2008; Ben-David, Shalev-Shwartz, and Urner 2012).”
Counterfactual reasoning and learning systems: the example of computational advertising (2012, background): “Importance sampling is widely used to deal with covariate shifts (Shimodaira, 2000; Sugiyama et al., 2007).”
Doubly Robust Policy Evaluation and Optimization (2014, background): “This setting is known as covariate shift (Shimodaira, 2000), where”
Few-Shot Adversarial Domain Adaptation (2017, background): “Naively training a classifier on one dataset for testing on another is known to produce sub-optimal results, because an effect known as dataset bias [42, 57, 56] or covariate shift [51] occurs due to a difference in the distributions of the images between the datasets.”