This week has been a momentous one for the US stock market. Lyft, the ride-hailing company, sold its shares to the public for the first time, heralding a march of the "unicorns". A stream of these businesses - which are defined as private, venture capital-backed firms worth over $1bn - are set to follow, including Lyft's rival Uber, online scrapbook company Pinterest and home-sharing site AirBnB. And they are attracting some staggering valuations. Uber, for example, could be worth as much as $120bn when it floats.

Abstract: "In this talk I will cover some of the recent work out of the Socially Intelligent Machines Lab at UT Austin (http://sim.ece.utexas.edu/research.html). The vision of our research is to enable robots to function in dynamic human environments by allowing them to flexibly adapt their skill set via learning interactions with end-users. We explore the ways in which Machine Learning agents can exploit principles of human social learning, and breakdown assumptions about what "data" will be like, when the source of that data is an average human teacher. I will cover our work on interactive reinforcement learning algorithms that model the attention of the teacher; coupling learning from demonstration with simulation to make the best use of valuable interactions with people; and algorithms for re-using previously learned tasks in new contexts with the help of a teacher's hints and corrections. In the latter part of the talk, I will put on my other hat, as co-founder and CEO of Diligent Robotics (http://diligentrobots.com/about) to tell you about how we are translating our research on adapting to human environments into a commercial product. Our first product, Moxi, is a robot assistant that works alongside and supports clinical care teams in hospitals. Moxi was launched into beta trials late last year, and has been deployed in four hospitals across Texas to date."

USA TODAY consumer editor Michelle Maltais and Common Sense Media executive editor Sierra Filucci share ways to manage your household's attachment to media and electronic devices. There are a few things parents often fret about when it comes to their children playing video games: Is the game's content appropriate for their child? Are they having trouble tearing themselves away from the console? Just who are they talking to online in that headset? Compounding these concerns is the fact mom and dad can't always be around. Some consoles are portable, too, such as the Nintendo Switch, which a child can take to their bedroom and close the door.

We extend probabilistic action language pBC+ with the notion of utility as in decision theory. The semantics of the extended pBC+ can be defined as a shorthand notation for a decision-theoretic extension of the probabilistic answer set programming language LPMLN. Alternatively, the semantics of pBC+ can also be defined in terms of Markov Decision Process (MDP), which in turn allows for representing MDP in a succinct and elaboration tolerant way as well as to leverage an MDP solver to compute pBC+. The idea led to the design of the system pbcplus2mdp, which can find an optimal policy of a pBC+ action description using an MDP solver.

Optimal auction design is one of the cornerstones of economic theory. It is of great practical importance, as auctions are used across industries and by the public sector to organize the sale of their products and services. Concrete examples are the US FCC Incentive Auction, the sponsored search auctions conducted by web search engines such as Google, or the auctions run on platforms such as eBay. In the standard independent private valuations model, each bidder has a valuation function over subsets of items, drawn independently from not necessarily identical distributions. It is assumed that the auctioneer knows the distributions and can (and will) use this information in designing the auction. A major difficulty in designing auctions is that valuations are private and bidders need to be incentivized to report their valuations truthfully. The goal is to learn an incentive compatible auction that maximizes revenue. We would like to thank Yang Cai, Vincent Conitzer, Yannai Gonczarowski, Constantinos Daskalakis, Glenn Ellison, Sergiu Hart, Ron Lavi, Kevin Leyton-Brown, Shengwu Li, Noam Nisan, Parag Pathak, Alexander Rush, Karl Schlag, Alex Wolitzky, participants in the Economics and Computation Reunion Workshop at the Simons Institute, the NIPS'17 Workshop on Learning in the Presence of Strategic Behavior, a Dagstuhl Workshop on Computational Learning Theory meets Game Theory, the EC'18 Workshop on Algorithmic Game Theory and Data Science, the Annual Congress of the German Economic Association, participants in seminars at LSE, Technion, Hebrew, Google, HBS, MIT, and the anonymous reviewers on earlier versions of this paper for their helpful feedback. The first version of this paper was posted on arXiv on June 12, 2017.

The recent surge of text-based online counseling applications enables us to collect and analyze interactions between counselors and clients. A dataset of those interactions can be used to learn to automatically classify the client utterances into categories that help counselors in diagnosing client status and predicting counseling outcome. With proper anonymization, we collect counselor-client dialogues, define meaningful categories of client utterances with professional counselors, and develop a novel neural network model for classifying the client utterances. The central idea of our model, ConvMFiT, is a pre-trained conversation model which consists of a general language model built from an out-of-domain corpus and two role-specific language models built from unlabeled in-domain dialogues. The classification result shows that ConvMFiT outperforms state-of-the-art comparison models. Further, the attention weights in the learned model confirm that the model finds expected linguistic patterns for each category.

Deep learning has been successfully used in numerous applications because of its outstanding performance and the ability to avoid manual feature engineering. One such application is electroencephalogram (EEG) based brain-computer interface (BCI), where multiple convolutional neural network (CNN) models have been proposed for EEG classification. However, it has been found that deep learning models can be easily fooled with adversarial examples, which are normal examples with small deliberate perturbations. This paper proposes an unsupervised fast gradient sign method (UFGSM) to attack three popular CNN classifiers in BCIs, and demonstrates its effectiveness. We also verify the transferability of adversarial examples in BCIs, which means we can perform attacks even without knowing the architecture and parameters of the target models, or the datasets they were trained on. To our knowledge, this is the first study on the vulnerability of CNN classifiers in EEG-based BCIs, and hopefully will trigger more attention on the security of BCI systems.

In the context of fake news, bias, and propaganda, we study two important but relatively under-explored problems: (i) trustworthiness estimation (on a 3-point scale) and (ii) political ideology detection (left/right bias on a 7-point scale) of entire news outlets, as opposed to evaluating individual articles. In particular, we propose a multi-task ordinal regression framework that models the two problems jointly. This is motivated by the observation that hyper-partisanship is often linked to low trustworthiness, e.g., appealing to emotions rather than sticking to the facts, while center media tend to be generally more impartial and trustworthy. We further use several auxiliary tasks, modeling centrality, hyperpartisanship, as well as left-vs.-right bias on a coarse-grained scale. The evaluation results show sizable performance gains by the joint models over models that target the problems in isolation.

In this work, we analyze the suitability of deep neural networks (DNNs) for the numerical solution of parametric problems. Such problems connect a parameter space with a solution state space via a so-called parametric map, [53]. One special case of such a parametric problem arises when the parametric map results from solving a partial differential equation (PDE) and the parameters describe physical or geometrical constraints of the PDE such as, for example, the shape of the physical domain, boundary conditions, or a source term. Applications that lead to these problems include modeling unsteady and steady heat and mass transfer, acoustics, fluid mechanics, or electromagnetics, [34]. Solving a parametric PDE for every point in the parameter space of interest individually typically leads to two types of problems.

In such applications, a fundamental statistical tool is tensor regression, a modern high-dimensional regression method that relates a scalar response to tensor covariates. For example, in neuroimaging analysis, an important objective is to predict clinical outcomes using subjects' brain imaging data. This can be formulated as a tensor regression problem by treating the clinical outcomes as the response and the brain images as the tensor covariates. Another example is in the study of how advertisement placement affect users' clicking behavior in online advertising. This again can be formulated as a tensor regression problem by treating the daily overall click-through rate (CTR) as the response and the tensor that summarizes the impressions (i.e., view counts) of different advertisements on different devices (e.g., phone, computer, etc.) as the covariate. In Section 6, we consider such an online advertising application.