As astronauts move deeper into space they must also become more autonomous from mission control on Earth. As a result, astronauts must take on additional responsibilities for jobs typically performed by flight controllers today, and crew workload and training requirements are expected to increase. Robotic automation has potential to reduce crew workload and training needs. Additionally robots with some level of autonomy can reduce human risk by per-forming hazardous tasks that crew would otherwise have to perform. We are working with NASA to investigate new concepts of operation for astronauts interacting with autonomous robots in space, including remote supervision of a planetary robot by an astronaut orbiting the planet and remote understanding of robotic activities without eyes-on monitoring. We also are developing techniques for computing and analyzing agent performance for the roles and responsibilities needed for these ConOps, and have developed software to compute these performance measures for humans and robots in-line during mission operations. We describe results of using this software to monitor rover performance during multiple NASA robotic field tests and analog mission simulations.

This paper introduces the Affordance Template framework used to supervise task behaviors on the NASA-JSC Valkyrie robot at the 2013 DARPA Robotics Challenge (DRC) Trials. This framework provides graphical interfaces to human supervisors that are adjustable based on the run-time environmental context (e.g., size, location, and shape of objects that the robot must interact with, etc.). Additional improvements, described below, inject degrees of autonomy into instantiations of affordance templates at run-time in order to enable efficient human supervision of the robot for accomplishing tasks.

We present theoretical and empirical results demonstrating the usefulness of social choice functions in crowdsourcing for participatory democracies. First, we demonstrate the scalability of social choice functions by defining a natural notion of epsilon-approximation, and giving algorithms which efficiently elicit such approximations for two prominent social choice functions: the Borda rule and the Condorcet winner. This result circumvents previous prohibitive lower bounds and is surprisingly strong: even if the number of ideas is as large as the number of participants, each participant will only have to make a logarithmic number of comparisons, an exponential improvement over the linear number of comparisons previously needed. Second, we apply these ideas to Finland's recent off-road traffic law reform, an experiment on participatory democracy in real life. This allows us to verify the scaling predicted in our theory and show that the constant involved is also not large. In addition, by collecting data on the time that users take to complete rankings of varying sizes, we observe that eliciting partial rankings can further decrease elicitation time as compared to the common method of eliciting pairwise comparisons.

While temporal behavioral patterns can be discerned to underlie real crowd work, prior studies have typically modeled worker performance under a simplified i.i.d. assumption. To better model such temporal worker behavior, we propose a time-series label prediction model for crowd work. This latent variable model captures and summarizes past worker behavior, enabling us to better predict the quality of each worker's next label. Given inherent uncertainty in prediction, we also investigate a decision reject option to balance the tradeoff between prediction accuracy vs. coverage. Results show our model improves accuracy of both label prediction on real crowd worker data, as well as data quality overall.

A wide variety of application domains are concerned with data consisting of entities and their relationships or connections, formally represented as graphs. Within these diverse application areas, a common problem of interest is the detection of a subset of entities whose connectivity is anomalous with respect to the rest of the data. While the detection of such anomalous subgraphs has received a substantial amount of attention, no application-agnostic framework exists for analysis of signal detectability in graph-based data. In this paper, we describe a framework that enables such analysis using the principal eigenspace of a graph's residuals matrix, commonly called the modularity matrix in community detection. Leveraging this analytical tool, we show that the framework has a natural power metric in the spectral norm of the anomalous subgraph's adjacency matrix (signal power) and of the background graph's residuals matrix (noise power). We propose several algorithms based on spectral properties of the residuals matrix, with more computationally expensive techniques providing greater detection power. Detection and identification performance are presented for a number of signal and noise models, including clusters and bipartite foregrounds embedded into simple random backgrounds as well as graphs with community structure and realistic degree distributions. The trends observed verify intuition gleaned from other signal processing areas, such as greater detection power when the signal is embedded within a less active portion of the background. We demonstrate the utility of the proposed techniques in detecting small, highly anomalous subgraphs in real graphs derived from Internet traffic and product co-purchases.

We present a novel approach to learn binary classifiers when only positive and unlabeled instances are available (PU learning). This problem is routinely cast as a supervised task with label noise in the negative set. We use an ensemble of SVM models trained on bootstrap resamples of the training data for increased robustness against label noise. The approach can be considered in a bagging framework which provides an intuitive explanation for its mechanics in a semi-supervised setting. We compared our method to state-of-the-art approaches in simulations using multiple public benchmark data sets. The included benchmark comprises three settings with increasing label noise: (i) fully supervised, (ii) PU learning and (iii) PU learning with false positives. Our approach shows a marginal improvement over existing methods in the second setting and a significant improvement in the third. Frank De Smet is a member of the medical management department of the National Alliance of Christian Mutualities. Accepted at Neurocomputing: SI on Advances in Learning with Label Noise 20/10/2014 1. Introduction Training binary classifiers on positive and unlabeled data is referred to as PU learning [31]. The absence of known negative training instances warrants appropriate learning methods. Inaccurate label information can be more problematic than attribute noise [45]. Specialised PU learning approaches are recommended when (i) negative labels cannot be acquired, (ii) the training data contains a large amount of false negatives or (iii) the positive set has many outliers. Practical applications of PU learning typically feature large, imbalanced training sets with a small amount of labeled (positive) and a large amount of unlabeled training instances. The PU learning problem arises in various settings, including web page classification [44], intrusion detection [26] and bioinformatics tasks such as variant prioritization [42], gene prioritization [1, 35] and virtual screening of drug compounds [41]. Though these applications share a common underlying learning problem, the final evaluation criteria may be fundamentally different.

Structured sparsity is an important modeling tool that expands the applicability of convex formulations for data analysis, however it also creates significant challenges for efficient algorithm design. In this paper we investigate the generalized conditional gradient (GCG) algorithm for solving structured sparse optimization problems---demonstrating that, with some enhancements, it can provide a more efficient alternative to current state of the art approaches. After providing a comprehensive overview of the convergence properties of GCG, we develop efficient methods for evaluating polar operators, a subroutine that is required in each GCG iteration. In particular, we show how the polar operator can be efficiently evaluated in two important scenarios: dictionary learning and structured sparse estimation. A further improvement is achieved by interleaving GCG with fixed-rank local subspace optimization. A series of experiments on matrix completion, multi-class classification, multi-view dictionary learning and overlapping group lasso shows that the proposed method can significantly reduce the training cost of current alternatives.

Bayesian entity resolution merges together multiple, noisy databases and returns the minimal collection of unique individuals represented, together with their true, latent record values. Bayesian methods allow flexible generative models that share power across databases as well as principled quantification of uncertainty for queries of the final, resolved database. However, existing Bayesian methods for entity resolution use Markov monte Carlo method (MCMC) approximations and are too slow to run on modern databases containing millions or billions of records. Instead, we propose applying variational approximations to allow scalable Bayesian inference in these models. We derive a coordinate-ascent approximation for mean-field variational Bayes, qualitatively compare our algorithm to existing methods, note unique challenges for inference that arise from the expected distribution of cluster sizes in entity resolution, and discuss directions for future work in this domain.

Frank-Wolfe algorithms for convex minimization have recently gained considerable attention from the Optimization and Machine Learning communities, as their properties make them a suitable choice in a variety of applications. However, as each iteration requires to optimize a linear model, a clever implementation is crucial to make such algorithms viable on large-scale datasets. For this purpose, approximation strategies based on a random sampling have been proposed by several researchers. In this work, we perform an experimental study on the effectiveness of these techniques, analyze possible alternatives and provide some guidelines based on our results.

On the Properties of Neural Machine Translation: Encoder-Decoder Approaches Kyunghyun Cho Bart van Merri enboer Universit e de Montr eal Dzmitry Bahdanau Jacobs University, Germany Yoshua Bengio Universit e de Montr eal, CIFAR Senior Fellow Abstract Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder-Decoder and a newly proposed gated recursive con-volutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically. 1 Introduction A new approach for statistical machine translation based purely on neural networks has recently been proposed (Kalchbrenner and Blunsom, 2013; Sutskever et al., 2014). This new approach, which we refer to as neural machine translation, is inspired by the recent trend of deep representational learning. All the neural network models used in (Kalchbrenner and Blunsom, 2013; Sutskever et al., 2014; Cho et al., 2014) consist of an encoder and a decoder.