Machine learning algorithms increasingly influence our decisions and interact with us in all parts of our daily lives. Therefore, just as we consider the safety of power plants, highways, and a ...variety of other engineered socio-technical systems, we must also take into account the safety of systems involving machine learning. Heretofore, the definition of safety has not been formalized in a machine learning context. In this article, we do so by defining machine learning safety in terms of risk, epistemic uncertainty, and the harm incurred by unwanted outcomes. We then use this definition to examine safety in all sorts of applications in cyber-physical systems, decision sciences, and data products. We find that the foundational principle of modern statistical machine learning, empirical risk minimization, is not always a sufficient objective. We discuss how four different categories of strategies for achieving safety in engineering, including inherently safe design, safety reserves, safe fail, and procedural safeguards can be mapped to a machine learning context. We then discuss example techniques that can be adopted in each category, such as considering interpretability and causality of predictive models, objective functions beyond expected prediction accuracy, human involvement for labeling difficult or rare examples, and user experience design of software and open data.
Racial discrimination in decision-making scenarios such as police arrests appears to be a violation of expected utility theory. Drawing on results from the science of information, we discuss an ...information-based model of signal detection over a population that generates such behavior as an alternative explanation to taste-based discrimination by the decision maker or differences among the racial populations. This model uses the decision rule that maximizes expected utility-the likelihood ratio test-but constrains the precision of the threshold to a small discrete set. The precision constraint follows from both bounded rationality in human recollection and finite training data for estimating priors. When combined with social aspects of human decision making and precautionary cost settings, the model predicts the own-race bias that has been observed in several econometric studies.
We propose a new algorithm for estimation, prediction, and recommendation named the collaborative Kalman filter. Suited for use in collaborative filtering settings encountered in recommendation ...systems with significant temporal dynamics in user preferences, the approach extends probabilistic matrix factorization in time through a state-space model. This leads to an estimation procedure with parallel Kalman filters and smoothers coupled through item factors. Learning of global parameters uses the expectation-maximization algorithm. The method is compared to existing techniques and performs favorably on both generated data and real-world movie recommendation data.
A synergistic future for AI and ecology Han, Barbara A.; Varshney, Kush R.; LaDeau, Shannon ...
Proceedings of the National Academy of Sciences - PNAS,
09/2023, Letnik:
120, Številka:
38
Journal Article
Recenzirano
Odprti dostop
Research in both ecology and AI strives for predictive understanding of complex systems, where nonlinearities arise from multidimensional interactions and feedbacks across multiple scales. After a ...century of independent, asynchronous advances in computational and ecological research, we foresee a critical need for intentional synergy to meet current societal challenges against the backdrop of global change. These challenges include understanding the unpredictability of systems-level phenomena and resilience dynamics on a rapidly changing planet. Here, we spotlight both the promise and the urgency of a convergence research paradigm between ecology and AI. Ecological systems are a challenge to fully and holistically model, even using the most prominent AI technique today: deep neural networks. Moreover, ecological systems have emergent and resilient behaviors that may inspire new, robust AI architectures and methodologies. We share examples of how challenges in ecological systems modeling would benefit from advances in AI techniques that are themselves inspired by the systems they seek to model. Both fields have inspired each other, albeit indirectly, in an evolution toward this convergence. We emphasize the need for more purposeful synergy to accelerate the understanding of ecological resilience whilst building the resilience currently lacking in modern AI systems, which have been shown to fail at times because of poor generalization in different contexts. Persistent epistemic barriers would benefit from attention in both disciplines. The implications of a successful convergence go beyond advancing ecological disciplines or achieving an artificial general intelligence—they are critical for both persisting and thriving in an uncertain future.
The deployment of machine learning (ML) systems in applications with societal impact has motivated the study of fairness for marginalized groups. Often, the protected attribute is absent from the ...training dataset for legal reasons. However, datasets still contain proxy attributes that capture protected information and can inject unfairness in the ML model. Some deployed systems allow auditors, decision makers, or affected users to report issues or seek recourse by flagging individual samples. In this work, we examine such systems and consider a feedback-based framework where the protected attribute is unavailable and the flagged samples are indirect knowledge. The reported samples are used as guidance to identify the proxy attributes that are causally dependent on the (unknown) protected attribute. We work under the causal interventional fairness paradigm. Without requiring the underlying structural causal model a priori, we propose an approach that performs conditional independence tests on observed data to identify such proxy attributes. We theoretically prove the optimality of our algorithm, bound its complexity, and complement it with an empirical evaluation demonstrating its efficacy on various real-world and synthetic datasets.
Sparse signal representations and approximations from overcomplete dictionaries have become an invaluable tool recently. In this paper, we develop a new, heuristic, graph-structured, sparse signal ...representation algorithm for overcomplete dictionaries that can be decomposed into subdictionaries and whose dictionary elements can be arranged in a hierarchy. Around this algorithm, we construct a methodology for advanced image formation in wide-angle synthetic aperture radar (SAR), defining an approach for joint anisotropy characterization and image formation. Additionally, we develop a coordinate descent method for jointly optimizing a parameterized dictionary and recovering a sparse representation using that dictionary. The motivation is to characterize a phenomenon in wide-angle SAR that has not been given much attention before: migratory scattering centers, i.e., scatterers whose apparent spatial location depends on aspect angle. Finally, we address the topic of recovering solutions that are sparse in more than one objective domain by introducing a suitable sparsifying cost function. We encode geometric objectives into SAR image formation through sparsity in two domains, including the normal parameter space of the Hough transform.
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We ...propose a convex optimization for learning a data transformation with three goals: controlling group discrimination, limiting distortion in individual data samples, and preserving utility. Several theoretical properties are established, including conditions for convexity, a characterization of the impact of limited sample size on discrimination and utility guarantees, and a connection between discrimination and estimation. Two instances of the proposed optimization are applied to datasets, including one on real-world criminal recidivism. Results show that discrimination can be greatly reduced at a small cost in classification accuracy and with precise control of individual distortion.
In previous work reported in these Transactions, we proposed a new distortion measure for the quantization of prior probabilities that are used in the threshold of likelihood ratio test detection: ...Bayes risk error. In this correspondence, we show that the Bayes risk error is a member of the class of Bregman divergences and discuss the implications of this fact.
•Zika and other mosquito-borne flaviviruses persist in wild primates.•High biodiversity and low data availability prevent targeted surveillance.•Imputation and machine learning confront data sparsity ...to predict primate hosts.•Hosts with highest risk of Zika positivity are in close proximity to humans.•Targeted surveillance of predicted hosts and vectors may mitigate spillover risk.
The recent Zika virus (ZIKV) epidemic in the Americas ranks among the largest outbreaks in modern times. Like other mosquito-borne flaviviruses, ZIKV circulates in sylvatic cycles among primates that can serve as reservoirs of spillover infection to humans. Identifying sylvatic reservoirs is critical to mitigating spillover risk, but relevant surveillance and biological data remain limited for this and most other zoonoses. We confronted this data sparsity by combining a machine learning method, Bayesian multi-label learning, with a multiple imputation method on primate traits. The resulting models distinguished flavivirus-positive primates with 82% accuracy and suggest that species posing the greatest spillover risk are also among the best adapted to human habitations. Given pervasive data sparsity describing animal hosts, and the virtual guarantee of data sparsity in scenarios involving novel or emerging zoonoses, we show that computational methods can be useful in extracting actionable inference from available data to support improved epidemiological response and prevention.