Artificial intelligence (AI) systems have become increasingly popular in many areas. Nevertheless, AI technologies are still in their developing stages, and many issues need to be addressed. Among those, the reliability of AI systems needs to be demonstrated so that the AI systems can be used with confidence by the general public. In this paper, we provide statistical perspectives on the reliability of AI systems. Different from other considerations, the reliability of AI systems focuses on the time dimension. That is, the system can perform its designed functionality for the intended period. We introduce a so-called SMART statistical framework for AI reliability research, which includes five components: Structure of the system, Metrics of reliability, Analysis of failure causes, Reliability assessment, and Test planning. We review traditional methods in reliability data analysis and software reliability, and discuss how those existing methods can be transformed for reliability modeling and assessment of AI systems. We also describe recent developments in modeling and analysis of AI reliability and outline statistical research challenges in this area, including out-of-distribution detection, the effect of the training set, adversarial attacks, model accuracy, and uncertainty quantification, and discuss how those topics can be related to AI reliability, with illustrative examples. Finally, we discuss data collection and test planning for AI reliability assessment and how to improve system designs for higher AI reliability. The paper closes with some concluding remarks.

Motivated by neuroscientific and clinical applications, we empirically examine whether observational measures of information flow can suggest interventions. We do so by performing experiments on artificial neural networks in the context of fairness in machine learning, where the goal is to induce fairness in the system through interventions. Using our recently developed $M$-information flow framework, we measure the flow of information about the true label (responsible for accuracy, and hence desirable), and separately, the flow of information about a protected attribute (responsible for bias, and hence undesirable) on the edges of a trained neural network. We then compare the flow magnitudes against the effect of intervening on those edges by pruning. We show that pruning edges that carry larger information flows about the protected attribute reduces bias at the output to a greater extent. This demonstrates that $M$-information flow can meaningfully suggest targets for interventions, answering the title's question in the affirmative. We also evaluate bias-accuracy tradeoffs for different intervention strategies, to analyze how one might use estimates of desirable and undesirable information flows (here, accuracy and bias flows) to inform interventions that preserve the former while reducing the latter.

Deep neural networks are susceptible to adversarially crafted, small and imperceptible changes in the natural inputs. The most effective defense mechanism against these examples is adversarial training which constructs adversarial examples during training by iterative maximization of loss. The model is then trained to minimize the loss on these constructed examples. This min-max optimization requires more data, larger capacity models, and additional computing resources. It also degrades the standard generalization performance of a model. Can we achieve robustness more efficiently? In this work, we explore this question from the perspective of knowledge transfer. First, we theoretically show the transferability of robustness from an adversarially trained teacher model to a student model with the help of mixup augmentation. Second, we propose a novel robustness transfer method called Mixup-Based Activated Channel Maps (MixACM) Transfer. MixACM transfers robustness from a robust teacher to a student by matching activated channel maps generated without expensive adversarial perturbations. Finally, extensive experiments on multiple datasets and different learning scenarios show our method can transfer robustness while also improving generalization on natural images.

This paper presents the PlanMiner-N algorithm, a domain learning technique based on the PlanMiner domain learning algorithm. The algorithm presented here improves the learning capabilities of PlanMiner when using noisy data as input. The PlanMiner algorithm is able to infer arithmetic and logical expressions to learn numerical planning domains from the input data, but it was designed to work under situations of incompleteness making it unreliable when facing noisy input data. In this paper, we propose a series of enhancements to the learning process of PlanMiner to expand its capabilities to learn from noisy data. These methods preprocess the input data by detecting noise and filtering it and study the learned action models learned to find erroneous preconditions/effects in them. The methods proposed in this paper were tested using a set of domains from the International Planning Competition (IPC). The results obtained indicate that PlanMiner-N improves the performance of PlanMiner greatly when facing noisy input data.

Higher-order tensor datasets are rising ubiquitously in modern data science applications, for instance, recommendation systems (Baltrunas et al., 2011; Bi et al., 2018), social networks (Bickel and Chen, 2009), genomics (Hore et al., 2016), and neuroimaging (Zhou et al., 2013). Tensor provides effective representation of data structure that classical vector-and matrix-based methods fail to capture. One example is music recommendation system (Baltrunas et al., 2011) that records ratings of songs from users on various contexts. This three-way tensor of user song context allows us to investigate interactions of users and songs in a context-specific manner. Another example is network dataset that records the connections among a set of nodes. Pairwise interactions are often insufficient to capture the complex relationships, whereas multi-way interactions improve the understanding of networks in molecular system (Young et al., 2018) and social networks (Han et al., 2020). In both examples, higher-order tensors represent multi-way interactions in an efficient way. Tensor estimation problem cannot be solved without imposing structures. An appropriate reordering of tensor entries often provides effective representation of the hidden salient structure.

Several instance-based explainability methods for finding influential training examples for test-time decisions have been proposed recently, including Influence Functions, TraceIn, Representer Point Selection, Grad-Dot, and Grad-Cos. Typically these methods are evaluated using LOO influence (Cook's distance) as a gold standard, or using various heuristics. In this paper, we show that all of the above methods are unstable, i.e., extremely sensitive to initialization, ordering of the training data, and batch size. We suggest that this is a natural consequence of how in the literature, the influence of examples is assumed to be independent of model state and other examples -- and argue it is not. We show that LOO influence and heuristics are, as a result, poor metrics to measure the quality of instance-based explanations, and instead propose to evaluate such explanations by their ability to detect poisoning attacks. Further, we provide a simple, yet effective baseline to improve all of the above methods and show how it leads to very significant improvements on downstream tasks.

Recently deep learning has been successfully applied to unsupervised active learning. However, current method attempts to learn a nonlinear transformation via an auto-encoder while ignoring the sample relation, leaving huge room to design more effective representation learning mechanisms for unsupervised active learning. In this paper, we propose a novel deep unsupervised Active Learning model via Learnable Graphs, named ALLG. ALLG benefits from learning optimal graph structures to acquire better sample representation and select representative samples. To make the learnt graph structure more stable and effective, we take into account $k$-nearest neighbor graph as a priori, and learn a relation propagation graph structure. We also incorporate shortcut connections among different layers, which can alleviate the well-known over-smoothing problem to some extent. To the best of our knowledge, this is the first attempt to leverage graph structure learning for unsupervised active learning. Extensive experiments performed on six datasets demonstrate the efficacy of our method.

Automated hyperparameter optimization (HPO) can support practitioners to obtain peak performance in machine learning models. However, there is often a lack of valuable insights into the effects of different hyperparameters on the final model performance. This lack of explainability makes it difficult to trust and understand the automated HPO process and its results. We suggest using interpretable machine learning (IML) to gain insights from the experimental data obtained during HPO with Bayesian optimization (BO). BO tends to focus on promising regions with potential high-performance configurations and thus induces a sampling bias. Hence, many IML techniques, such as the partial dependence plot (PDP), carry the risk of generating biased interpretations. By leveraging the posterior uncertainty of the BO surrogate model, we introduce a variant of the PDP with estimated confidence bands. We propose to partition the hyperparameter space to obtain more confident and reliable PDPs in relevant sub-regions. In an experimental study, we provide quantitative evidence for the increased quality of the PDPs within sub-regions.

Most existing classification methods aim to minimize the overall misclassification error rate, however, in applications, different types of errors can have different consequences. To take into account this asymmetry issue, two popular paradigms have been developed, namely the Neyman-Pearson (NP) paradigm and cost-sensitive (CS) paradigm. Compared to CS paradigm, NP paradigm does not require a specification of costs. Most previous works on NP paradigm focused on the binary case. In this work, we study the multi-class NP problem by connecting it to the CS problem, and propose two algorithms. We extend the NP oracle inequalities and consistency from the binary case to the multi-class case, and show that our two algorithms enjoy these properties under certain conditions. The simulation and real data studies demonstrate the effectiveness of our algorithms. To our knowledge, this is the first work to solve the multi-class NP problem via cost-sensitive learning techniques with theoretical guarantees. The proposed algorithms are implemented in the R package "npcs" on CRAN.

Unlike matrix completion, no algorithm for the tensor completion problem has so far been shown to achieve the information-theoretic sample complexity rate. This paper develops a new algorithm for the special case of completion for nonnegative tensors. We prove that our algorithm converges in a linear (in numerical tolerance) number of oracle steps, while achieving the information-theoretic rate. Our approach is to define a new norm for nonnegative tensors using the gauge of a specific 0-1 polytope that we construct. Because the norm is defined using a 0-1 polytope, this means we can use integer linear programming to solve linear separation problems over the polytope. We combine this insight with a variant of the Frank-Wolfe algorithm to construct our numerical algorithm, and we demonstrate its effectiveness and scalability through experiments.