Over the past decade, random forest models have become widely used as a robust method for high-dimensional data regression tasks. In part, the popularity of these models arises from the fact that they require little hyperparameter tuning and are not very susceptible to overfitting. Random forest regression models are comprised of an ensemble of decision trees that independently predict the value of a (continuous) dependent variable; predictions from each of the trees are ultimately averaged to yield an overall predicted value from the forest. Using a suite of representative real-world datasets, we find a systematic bias in predictions from random forest models. We find that this bias is recapitulated in simple synthetic datasets, regardless of whether or not they include irreducible error (noise) in the data, but that models employing boosting do not exhibit this bias. Here we demonstrate the basis for this problem, and we use the training data to define a numerical transformation that fully corrects it. Application of this transformation yields improved predictions in every one of the real-world and synthetic datasets evaluated in our study.

High-dimensional autoregressive point processes model how current events trigger or inhibit future events, such as activity by one member of a social network can affect the future activity of his or her neighbors. While past work has focused on estimating the underlying network structure based solely on the times at which events occur on each node of the network, this paper examines the more nuanced problem of estimating context-dependent networks that reflect how features associated with an event (such as the content of a social media post) modulate the strength of influences among nodes. Specifically, we leverage ideas from compositional time series and regularization methods in machine learning to conduct network estimation for high-dimensional marked point processes. Two models and corresponding estimators are considered in detail: an autoregressive multinomial model suited to categorical marks and a logistic-normal model suited to marks with mixed membership in different categories. Importantly, the logistic-normal model leads to a convex negative log-likelihood objective and captures dependence across categories. We provide theoretical guarantees for both estimators, which we validate by simulations and a synthetic data-generating model. We further validate our methods through two real data examples and demonstrate the advantages and disadvantages of both approaches.

We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms. Theory-inspired simulations show that the widely-used temporal difference (TD) algorithm is strictly suboptimal when evaluated in a non-asymptotic setting, even when combined with Polyak-Ruppert iterate averaging. We remedy this issue by introducing and analyzing variance-reduced forms of stochastic approximation, showing that they achieve non-asymptotic, instance-dependent optimality up to logarithmic factors.

In this paper, we present an analysis of computationally generated mixed-modality definite referring expressions using combinations of gesture and linguistic descriptions. In doing so, we expose some striking formal semantic properties of the interactions between gesture and language, conditioned on the introduction of content into the common ground between the (computational) speaker and (human) viewer, and demonstrate how these formal features can contribute to training better models to predict viewer judgment of referring expressions, and potentially to the generation of more natural and informative referring expressions.

But even by the usual standards, artificial intelligence has had a turbulent run. Is AI a society-renewing hero or a jobs-destroying villain? As always, the truth is not so categorical. At more than 1,000 pages, Thomas Piketty's doorstop sequel to his previous opus, Capital in the Twenty-First Century, does not disappoint. But whether it will fundamentally change the global debate about inequality is an open question. As a general-purpose technology, AI will be what we make of it, with its ultimate impact determined by the governance frameworks we build.

In another week that saw mainstream news dominated by the spread of COVID-19, FindBiometrics readers managed to keep the virus out of the latest top stories roundup. Instead, this week's collection of our most popular articles is dominated by facial recognition news, together with a bit of FinTech and a big announcement from the Department of Homeland Security. Starting with the latter, this week brought a call for submissions for the third-ever Biometric Technology Rally. This time, the DHS's Science and Technology Directorate is focused on finding solutions that can identify small groups of people within crowded environments: In FinTech news, meanwhile, FIS announced this week the launch of a new 3-D Secure payment authentication service. Another facial recognition specialist, Onfido, also got some attention with its news that it has once again been listed in CB Insights' AI 100 ranking.

Whereas 4G brought us the network speeds necessary for online apps and mobile-streaming, 5G represents a monumental leap forward. Beyond the improvements to our existing ecosystem of devices--more speed and better stability--researchers believe that 5G can serve as the underpinning for fully-connected industries and cities. Change doesn't happen overnight, and for us to experience 5G's true potential, we'll need to be patient. In light of this, today's infographic from Raconteur visualizes the forecasted impact of 5G to help us identify the countries and industries that will most effectively leverage its power. To make this easier to digest, here are the five industries which stand to benefit the most.

Israel is no stranger to innovation. Widely acknowledged as a Startup Nation, Israel has focussed exceptional levels of time and effort on building a ripe environment in which new tech companies can flourish. Towards the end of the 2010s, it became clear that there was a national push towards the development of Artificial Intelligence startups within urban hubs like Tel-Aviv. AI is set to generate revenues in excess of $10 billion over the coming years, and as a result, AI-based investments have been surging. In fact, as much as 37% of the capital raised in recent years was reserved for AI companies, according to Science Business.

Due to their unique oversight, governments have a surplus of data at their fingertips. Used properly, this available data could enable them to create beneficial programs that tackle problems in economics, policy, transportation, and civic life. Unfortunately, the majority of that data is untapped. Here are the facts about AI startups needing data, and how that helps governments. All hope is not lost, though.

Artificial intelligence is all the rage these days. In the popular media, regular cyber systems seem almost passe, as writers focus on AI and conjure up images of everything from real-life Terminator robots to more benign companions. In intelligence circles, China's uses of closed-circuit television, facial recognition technology, and other monitoring systems suggest the arrival of Big Brother--if not quite in 1984, then only about forty years later. At the Pentagon, legions of officers and analysts talk about the AI race with China, often with foreboding admonitions that the United States cannot afford to be second in class in this emerging realm of technology. In policy circles, people wonder about the ethics of AI--such as whether we can really delegate to robots the ability to use lethal force against America's enemies, however bad they may be.