With its bright-yellow armored body, grippy tank-like treads, plow nose and water cannon, the Los Angeles Fire Department's latest piece of equipment looks more like a Star Wars sidekick than a firefighting assistant. But this mini robot tanker is an inferno buster that pack a powerful punch of water or foam and can go where firefighters otherwise can't. The LAFD on Tuesday became the first fire department in the nation to acquire the Robotics Systems 3, a droid on steroids. LAFD Chief Ralph Terrazas said firefighters put their lives on the line when battling blazes. This year, 11 LAFD crew members were severely injured when a fireball engulfed four downtown buildings after a massive explosion that was ignited by hazardous materials.

Hacking involves a lot of research. The first step is finding as much public documentation as possible, then getting access to a vehicle, and finally spending as much time poking at the vehicle's interfaces as possible. However, we have to look at this from a return on investment (ROI) standpoint too. If my costs to buy or acquire the vehicle and spend a week or two with it were high, then I might not have reason to simply use this exploit for fun, but may have motivation to hold onto it. But if I wait too long a fix for the exploit may be available, thus negating my time and effort.

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem. By introducing an entropy premium, we obtain a smooth asymptotic approximation to the value function. This yields a novel semi-index approximation of the optimal decision process, obtained numerically by solving a fixed point problem, which can be interpreted as explicitly balancing an exploration-exploitation trade-off. Performance of the resulting Asymptotic Randomised Control (ARC) algorithm compares favourably with other approaches to correlated multi-armed bandits.

Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution shift between different environments during training in order to obtain more robust models. We propose a new gradient-based learning framework whose objective function is derived from the ICM principle. We show theoretically and experimentally that neural networks trained in this framework focus on relations remaining invariant across environments and ignore unstable ones. Moreover, we prove that the recovered stable relations correspond to the true causal mechanisms under certain conditions. In both regression and classification, the resulting models generalize well to unseen scenarios where traditionally trained models fail.

Healthcare programs such as Medicaid provide crucial services to vulnerable populations, but due to limited resources, many of the individuals who need these services the most languish on waiting lists. Survival models, e.g. the Cox proportional hazards model, can potentially improve this situation by predicting individuals' levels of need, which can then be used to prioritize the waiting lists. Providing care to those in need can prevent institutionalization for those individuals, which both improves quality of life and reduces overall costs. While the benefits of such an approach are clear, care must be taken to ensure that the prioritization process is fair or independent of demographic information-based harmful stereotypes. In this work, we develop multiple fairness definitions for survival models and corresponding fair Cox proportional hazards models to ensure equitable allocation of healthcare resources. We demonstrate the utility of our methods in terms of fairness and predictive accuracy on two publicly available survival datasets.

Machine learning models have traditionally been developed under the assumption that the training and test distributions match exactly. However, recent success in few-shot learning and related problems are encouraging signs that these models can be adapted to more realistic settings where train and test distributions differ. Unfortunately, there is severely limited theoretical support for these algorithms and little is known about the difficulty of these problems. In this work, we provide novel information-theoretic lower-bounds on minimax rates of convergence for algorithms that are trained on data from multiple sources and tested on novel data. Our bounds depend intuitively on the information shared between sources of data, and characterize the difficulty of learning in this setting for arbitrary algorithms. We demonstrate these bounds on a hierarchical Bayesian model of meta-learning, computing both upper and lower bounds on parameter estimation via maximum-a-posteriori inference.

Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups. For better model performance, previous studies learn to transform the topology of the input graph. However, these works only focus on optimizing the original nodes and edges, leaving the direction of augmenting existing data unexplored. In this paper, by simulating the generation process of graph signals, we propose a novel heuristic pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. Substantially enlarging the original training set with high-quality generated labeled data, our framework can effectively benefit downstream models. To justify the generality and practicality of ELCO, we couple it with the popular Graph Convolution Network and Graph Attention Network to perform extensive evaluations on three standard datasets. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art. We release our code and data on https://github.com/RingBDStack/ELCO to guarantee reproducibility.

Standard learning approaches are designed to perform well on average for the data distribution available at training time. Developing learning approaches that are not overly sensitive to the training distribution is central to research on domain- or out-of-distribution generalization, robust optimization and fairness. In this work we focus on links between research on domain generalization and algorithmic fairness -- where performance under a distinct but related test distributions is studied -- and show how the two fields can be mutually beneficial. While domain generalization methods typically rely on knowledge of disjoint "domains" or "environments", "sensitive" label information indicating which demographic groups are at risk of discrimination is often used in the fairness literature. Drawing inspiration from recent fairness approaches that improve worst-case performance without knowledge of sensitive groups, we propose a novel domain generalization method that handles the more realistic scenario where environment partitions are not provided. We then show theoretically and empirically how different partitioning schemes can lead to increased or decreased generalization performance, enabling us to outperform Invariant Risk Minimization with handcrafted environments in multiple cases. We also show how a re-interpretation of IRMv1 allows us for the first time to directly optimize a common fairness criterion, group-sufficiency, and thereby improve performance on a fair prediction task.

Use of a deep-learning convolutional neural network (CNN) -- a form of artificial intelligence -- can help reveal patterns on chest computed tomography (CT) scans that identify smokers at high long-term risk for lung cancer well beyond the Centers for Medicare & Medicaid Services (CMS) criteria for lung screening eligibility, according to the results of an analysis published in the Annals of Internal Medicine. Investigators sought to create and validate a CNN -- that is, the CXR-LC model -- with the ability to predict long-term incident lung cancer via the use of data typically available in a patient's electronic medical record, including chest radiographs, sex, age, and current smoking status. The CXR-LC model was developed in the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial, which included to total of 41,856 patients. The final CXR-LC model was validated in additional smokers from the PLCO study (n 5615; 12-year follow-up) and National Lung Screening Trial (NLST) heavy smokers (n 5493; 6-year follow-up). There were more current smokers (50.4% vs 20.2%, respectively) and higher mean pack-years (55.7 vs 35.4,

Manila – The head of the Philippines' military said Tuesday that the country is considering partnering with Japan to beef up its cyberdefense and drone capability as part of its force modernization program. Building cyberdefense and security infrastructure "is one aspect we are focusing on now and I think we can partner with Japan in this area," Chief of Staff Gen. Gilbert Gapay said during a media forum in Manila, noting a similar thrust for force upgrades within his country. The general said the military is also considering acquiring drones and other unmanned aerial vehicles from Japan to raise its maritime surveillance and monitoring capabilities. Japan has always been among the countries shortlisted for sourcing military hardware, based on studies conducted by different technical working groups, according to Gapay. In August, the Philippines signed a $103.5 million contract with Mitsubishi Electric Corp. for an air radar system, marking the first export of a newly made complete defense product since Japan eased its post-World War II arms export ban in 2014.