Search for: All records

Real-world data often violates the equal-variance assumption (homoscedasticity), making it essential to account for heteroscedastic noise in causal discovery. In this work, we explore heteroscedastic symmetric noise models (HSNMs), where the effect Y is modeled as Y = f(X) + σ(X)N, with X as the cause and N as independent noise following a symmetric distribution. We introduce a novel criterion for identifying HSNMs based on the skewness of the score (i.e., the gradient of the log density) of the data distribution. This criterion establishes a computationally tractable measurement that is zero in the causal direction but nonzero in the anticausal direction, enabling the causal direction discovery. We extend this skewness-based criterion to the multivariate setting and propose SkewScore, an algorithm that handles heteroscedastic noise without requiring the extraction of exogenous noise. We also conduct a case study on the robustness of SkewScore in a bivariate model with a latent confounder, providing theoretical insights into its performance. Empirical studies further validate the effectiveness of the proposed method. 

Many peer-review processes involve reviewers submitting their independent reviews, followed by a discussion between the reviewers of each paper. A common question among policymakers is whether the reviewers of a paper should be anonymous to each other during the discussion. We shed light on this question by conducting a randomized controlled trial at the Conference on Uncertainty in Artificial Intelligence (UAI) 2022 conference where reviewer discussions were conducted over a typed forum. We randomly split the reviewers and papers into two conditions–one with anonymous discussions and the other with non-anonymous discussions. We also conduct an anonymous survey of all reviewers to understand their experience and opinions. We compare the two conditions in terms of the amount of discussion, influence of seniority on the final decisions, politeness, reviewers’ self-reported experiences and preferences. Overall, this experiment finds small, significant differences favoring the anonymous discussion setup based on the evaluation criteria considered in this work. 

Abstract The rapidly expanding fleet of low‐altitude CubeSats equipped with energetic particle detectors brings new opportunities for monitoring the dynamics of the radiation belt and near‐Earth plasma sheet. Despite their small sizes, CubeSats can carry state‐of‐the‐art instruments that provide electron flux measurements with finer energy resolution and broader energy coverage, compared to conventional missions such as POES satellites. The recently launched CIRBE CubeSat measures 250–6,000 keV electrons with extremely high energy resolution, however, CIRBE typically only measures locally‐trapped electrons and cannot directly measure the precipitating electrons. This work aims to develop a technique for identifying indications of nightside precipitation using the locally‐trapped electron measurements by the CIRBE CubeSat. This study focuses on two main types of drivers for nightside precipitation: electron scattering by the curvature of magnetic field lines in the magnetotail current sheet and electron scattering by resonance with electromagnetic ion cyclotron (EMIC) waves. Using energy and pitch‐angle resolved electron fluxes from the low‐altitude ELFIN CubeSat, we reveal the features that distinguish between these two precipitation mechanisms based solely on locally‐trapped flux measurements. Then we present measurements from four CIRBE orbits and demonstrate the applicability of the proposed technique to the investigation of nightside precipitation using CIRBE observations, enabling separation between precipitation induced by curvature scattering and EMIC waves in nearby regions. Our study underscores the feasibility of employing high‐energy‐resolution CIRBE measurements for detecting nightside precipitation of relativistic electrons. Additionally, we briefly discuss outstanding scientific questions about these precipitation patterns that could be addressed with CIRBE measurements. 

We reveal and address the frequently overlooked yet important issue of disguised procedural unfairness, namely, the potentially inadvertent alterations on the behavior of neutral (i.e., not problematic) aspects of data generating process, and/or the lack of procedural assurance of the greatest benefit of the least advantaged individuals. Inspired by John Rawls's advocacy for pure procedural justice, we view automated decision-making as a microcosm of social institutions, and consider how the data generating process itself can satisfy the requirements of procedural fairness. We propose a framework that decouples the objectionable data generating components from the neutral ones by utilizing reference points and the associated value instantiation rule. Our findings highlight the necessity of preventing disguised procedural unfairness, drawing attention not only to the objectionable data generating components that we aim to mitigate, but also more importantly, to the neutral components that we intend to keep unaffected. 

Abstract The ion foreshock, filled with backstreaming foreshock ions, is very dynamic with many transient structures that disturb the bow shock and the magnetosphere‐ionosphere system. It has been shown that foreshock ions can be generated through either solar wind reflection at the bow shock or leakage from the magnetosheath. While solar wind reflection is widely believed to be the dominant generation process, our investigation using Time History of Events and Macroscale Interactions during Substorms mission observations reveals that the relative importance of magnetosheath leakage has been underestimated. We show from case studies that when the magnetosheath ions exhibit field‐aligned anisotropy, a large fraction of them attains sufficient field‐aligned speed to escape upstream, resulting in very high foreshock ion density. The observed foreshock ion density, velocity, phase space density, and distribution function shape are consistent with such an escape or leakage process. Our results suggest that magnetosheath leakage could be a significant contributor to the formation of the ion foreshock. Further characterization of the magnetosheath leakage process is a critical step toward building predictive models of the ion foreshock, a necessary step to better forecast foreshock‐driven space weather effects. 

Sparse online learning has received extensive attention during the past few years. Most of existing algorithms that utilize ℓ1-norm regularization or ℓ1-ball projection assume that the feature space is fixed or changes by following explicit constraints. However, this assumption does not always hold in many real applications. Motivated by this observation, we propose a new online learning algorithm tailored for data streams described by open feature spaces, where new features can be occurred, and old features may be vanished over various time spans. Our algorithm named RSOL provides a strategy to adapt quickly to such feature dynamics by encouraging sparse model representation with an ℓ1- and ℓ2-mixed regularizer. We leverage the proximal operator of the ℓ1,2-mixed norm and show that our RSOL algorithm enjoys a closed-form solution at each iteration. A sub-linear regret bound of our proposed algorithm is guaranteed with a solid theoretical analysis. Empirical results benchmarked on nine streaming datasets validate the effectiveness of the proposed RSOL method over three state-of-the-art algorithms. Keywords: online learning, sparse learning, streaming feature selection, open feature spaces, ℓ1,2 mixed norm 

Identifying latent variables and causal structures from observational data is essential to many real-world applications involving biological data, medical data, and unstructured data such as images and languages. However, this task can be highly challenging, especially when observed variables are generated by causally related latent variables and the relationships are nonlinear. In this work, we investigate the identification problem for nonlinear latent hierarchical causal models in which observed variables are generated by a set of causally related latent variables, and some latent variables may not have observed children. We show that the identifiability of causal structures and latent variables (up to invertible transformations) can be achieved under mild assumptions: on causal structures, we allow for multiple paths between any pair of variables in the graph, which relaxes latent tree assumptions in prior work; on structural functions, we permit general nonlinearity and multi-dimensional continuous variables, alleviating existing work's parametric assumptions. Specifically, we first develop an identification criterion in the form of novel identifiability guarantees for an elementary latent variable model. Leveraging this criterion, we show that both causal structures and latent variables of the hierarchical model can be identified asymptotically by explicitly constructing an estimation procedure. To the best of our knowledge, our work is the first to establish identifiability guarantees for both causal structures and latent variables in nonlinear latent hierarchical models.