While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts --- online content recommendation and sustainable abalone fisheries --- to underscore the applicability of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.

Regression models are used in a wide range of applications providing a powerful scientific tool for researchers from different fields. Linear models are often not sufficient to describe the complex relationship between input variables and a response. This relationship can be better described by non-linearities and complex functional interactions. Deep learning models have been extremely successful in terms of prediction although they are often difficult to specify and potentially suffer from overfitting. In this paper, we introduce a class of Bayesian generalized nonlinear regression models with a comprehensive non-linear feature space. Non-linear features are generated hierarchically, similarly to deep learning, but have additional flexibility on the possible types of features to be considered. This flexibility, combined with variable selection, allows us to find a small set of important features and thereby more interpretable models. A genetically modified Markov chain Monte Carlo algorithm is developed to make inference. Model averaging is also possible within our framework. In various applications, we illustrate how our approach is used to obtain meaningful non-linear models. Additionally, we compare its predictive performance with a number of machine learning algorithms.

DUBAI, UNITED ARAB EMIRATES – A small instrument inside the drones that targeted the heart of Saudi Arabia's oil industry and those in the arsenal of Yemen's Houthi rebels match components recovered in downed Iranian drones in Afghanistan and Iraq, two reports say. These gyroscopes have only been found inside drones manufactured by Iran, Conflict Armament Research said in a report released on Wednesday. That follows a recently released report from the United Nations saying its experts saw a similar gyroscope from an Iranian drone obtained by the U.S. military in Afghanistan, as well as in weapons shipments seized in the Arabian Sea bound for Yemen. The discovery further ties Iran to an attack that briefly halved Saudi Arabia's oil output and saw energy prices spike by a level unseen since the 1991 Gulf War. It also ties Iran to the arming of the rebel Houthis in Yemen's long civil war.

Since 2014, Russia has played a dominant role in the civil war hostilities in Syria where the testing of technology fresh out of research and development has been applied to measure results, graded by software systems. Such military upgrades launched in Syria and in Yemen include the SS-21 Scarab, the Uran-9 and the Ratnick-4 (robotics). A four day drill was held in December 2019 in the Gulf of Oman and the Indian Ocean. Participants were Russia, Iran, and China whose cooperation, unity, and military exchanges were evident during the drills. Russia's involvement should be considered in the light of a strategy.

True collectors are fascinating people; they're smart and persistent. As time goes on, everyday objects fall out of fashion and then, years later, clever collectors swoop in. Scouring the auction sites is a good way to find valuables and evaluate treasures. Tap or click here for 5 sneaky eBay scams to watch out for. When you're ready to look beyond eBay, I have you covered with links to government, law enforcement and Department of Treasury auctions.

Underwater photography is hard to get right. Special filters, artificial lights, and top-of-the-line underwater cameras can help, but there's still a lot of water between the camera and the object in the photo. We've become accustomed to the blue-green tint of underwater photography. How would the ocean look without water? What are the true colors of a coral reef?

The gradient boosting algorithm constructs a regression estimator using a linear combination of simple "base learners". In order to obtain a robust non-parametric regression estimator that is scalable to high dimensional problems we propose a robust boosting algorithm based on a two-stage approach, similar to what is done for robust linear regression: we first minimize a robust residual scale estimator, and then improve its efficiency by optimizing a bounded loss function. Unlike previous proposals, our algorithm does not need to compute an ad-hoc residual scale estimator in each step. Since our loss functions are typically non-convex, we propose initializing our algorithm with an $L_1$ regression tree, which is fast to compute. We also introduce a robust variable importance metric for variable selection that is calculated via a permutation procedure. Through simulated and real data experiments, we compare our method against gradient boosting with squared loss and other robust boosting methods in the literature. With clean data, our method works equally well as gradient boosting with the squared loss. With symmetric and asymmetrically contaminated data, we show that our proposed method outperforms in terms of prediction error and variable selection accuracy.

A team of researchers from the University of La Rochelle in France have converted albatrosses into de facto surveillance drones as part of a project to gather data on illegal fishing boats in the South Pacific and Indian Ocean. The team traveled to popular albatross nesting locations at Amsterdam Island and Kerguelen Island in the Indian Ocean north of Antarctica, and attached small sensors to 169 albatrosses in a procedure that took about 10 minutes per bird. The sensors weigh 65 grams, or around a seventh of a pound, and were equipped with a GPS receiver, a radar antenna, and a satellite communications monitor to track various boat communication systems. The devices were each powered by a small lithium battery that maintains a charge through a small solar panel, according to a report from ArsTechnica. The albatrosses covered more than 18 million square miles between East Africa and New Zealand, gathering data from more than 600,000 GPS locations.

Many classification applications require accurate probability estimates in addition to good class separation but often classifiers are designed focusing only on the latter. Calibration is the process of improving probability estimates by post-processing but commonly used calibration algorithms work poorly on small data sets and assume the classification task to be binary. Both of these restrictions limit their real-world applicability. Previously introduced Data Generation and Grouping algorithm alleviates the problem posed by small data sets and in this article, we will demonstrate that its application to multi-class problems is also possible which solves the other limitation. Our experiments show that calibration error can be decreased using the proposed approach and the additional computational cost is acceptable.

The UAE continues to places great importance to protecting the environment and promoting a green economy, placing sustainability at the forefront of its strategic priorities. This is in line with the UAE Vision 2021, which aims to build a sustainable environment, and a diversified and sustainable competitive economy that ensures a secure future for generations to come. Under the guidance of its wise leadership, the UAE has made great progress towards sustainability, driven by significant achievements in the adoption of advanced technologies to create a new reality and to build a leading global model for sustainable development. The UAE has recognised the importance of Artificial Intelligence (AI) as the cornerstone for achieving sustainability goals, at a time when this advanced technology is expected to contribute to the growth of the country's GDP by 35% until 2031, while also reducing government expenditures by 50% annually, cutting down the number of paper transactions and saving millions of work hours annually. The aim of the UAE Strategy for Artificial Intelligence 2031 is to improve government performance, accelerate the pace of achievements, and to create innovative and productive work environments that ensure high levels of productivity.