Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two-fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

We introduce an iterative optimization scheme for convex objectives consisting of a linear loss and a non-separable penalty, based on the expectation-consistent approximation and the vector approximate message-passing (VAMP) algorithm. Specifically, the penalties we approach are convex on a linear transformation of the variable to be determined, a notable example being total variation (TV). We describe the connection between message-passing algorithms -- typically used for approximate inference -- and proximal methods for optimization, and show that our scheme is, as VAMP, similar in nature to the Peaceman-Rachford splitting, with the important difference that stepsizes are set adaptively. Finally, we benchmark the performance of our VAMP-like iteration in problems where TV penalties are useful, namely classification in task fMRI and reconstruction in tomography, and show faster convergence than that of state-of-the-art approaches such as FISTA and ADMM in most settings.

Learning Bayesian networks from raw data can help provide insights into the relationships between variables. While real data often contains a mixture of discrete and continuous-valued variables, many Bayesian network structure learning algorithms assume all random variables are discrete. Thus, continuous variables are often discretized when learning a Bayesian network. However, the choice of discretization policy has significant impact on the accuracy, speed, and interpretability of the resulting models. This paper introduces a principled Bayesian discretization method for continuous variables in Bayesian networks with quadratic complexity instead of the cubic complexity of other standard techniques. Empirical demonstrations show that the proposed method is superior to the established minimum description length algorithm. In addition, this paper shows how to incorporate existing methods into the structure learning process to discretize all continuous variables and simultaneously learn Bayesian network structures.

Life-expectancy is a complex outcome driven by genetic, socio-demographic, environmental and geographic factors. Increasing socio-economic and health disparities in the United States are propagating the longevity-gap, making it a cause for concern. Earlier studies have probed individual factors but an integrated picture to reveal quantifiable actions has been missing. Amidst growing concerns about the further widening of healthcare inequality and differential access created by Artificial Intelligence, it is imperative to explore it's potential for illuminating biases and enabling transparent policy decisions. In this work, we reveal actionable interventions for decreasing the longevity-gap in the United States by analyzing a County-level data resource with healthcare, socio-economic, behavioral, education and demographic features. We learn an ensemble-averaged structure, draw inferences using the joint probability distribution and extend it to a Bayesian Decision Network for identifying policy actions. We draw quantitative estimates for the positive roles of diversity, preventive-care quality and stable-families within the unified framework of our decision network. Finally, we make this analysis and dashboard available as an interactive web-application for enabling users and policy-makers to validate our insights on bridging the longevity-gap and explore the ones beyond reported in this work.

When modeling real world domains we have to deal with information that is incomplete or that comes from sources with different trust levels. This motivates the need for managing uncertainty in the Semantic Web. To this purpose, we introduced a probabilistic semantics, named DISPONTE, in order to combine description logics with probability theory. The probability of a query can be then computed from the set of its explanations by building a Binary Decision Diagram (BDD). The set of explanations can be found using the tableau algorithm, which has to handle non-determinism. Prolog, with its efficient handling of non-determinism, is suitable for implementing the tableau algorithm. TRILL and TRILLP are systems offering a Prolog implementation of the tableau algorithm. TRILLP builds a pinpointing formula, that compactly represents the set of explanations and can be directly translated into a BDD. Both reasoners were shown to outperform state-of-the-art DL reasoners. In this paper, we present an improvement of TRILLP, named TORNADO, in which the BDD is directly built during the construction of the tableau, further speeding up the overall inference process. An experimental comparison shows the effectiveness of TORNADO. All systems can be tried online in the TRILL on SWISH web application at http://trill.ml.unife.it/.

Class labels are often imperfectly observed, due to mistakes and to genuine ambiguity among classes. We propose a new semi-supervised deep generative model that explicitly models noisy labels, called the Mislabeled VAE (M-VAE). The M-VAE can perform better than existing deep generative models which do not account for label noise. Additionally, the derivation of M-VAE gives new theoretical insights into the popular M1+M2 semi-supervised model.

We review common methods of solving for multi-class from binary and generalize them to a common framework. Since conditional probabilties are useful both for quantifying the accuracy of an estimate and for calibration purposes, these are a required part of the solution. There is some indication that the best solution for multi-class classification is dependent on the particular dataset. As such, we are particularly interested in data-driven solution design, whether based on a priori considerations or empirical examination of the data. Numerical results indicate that while a one-size-fits-all solution consisting of one-versus-one is appropriate for most datasets, a minority will benefit from a more customized approach. The techniques discussed in this paper allow for a large variety of multi-class configurations and solution methods to be explored so as to optimize classification accuracy, accuracy of conditional probabilities and speed.

Specialization and hierarchical organization are important features of efficient collaboration in economical, artificial, and biological systems. Here, we investigate the hypothesis that both features can be explained by the fact that each entity of such a system is limited in a certain way. We propose an information-theoretic approach based on a Free Energy principle, in order to computationally analyze systems of bounded rational agents that deal with such limitations optimally. We find that specialization allows to focus on fewer tasks, thus leading to a more efficient execution, but in turn requires coordination in hierarchical structures of specialized experts and coordinating units. Our results suggest that hierarchical architectures of specialized units at lower levels that are coordinated by units at higher levels are optimal, given that each unit's information-processing capability is limited and conforms to constraints on complexity costs.

We consider the problem of learning a binary classifier only from positive data and unlabeled data (PU learning). This problem arises in various practical situations, such as information retrieval and outlier detection (Elkan and Noto, 2008; Ward et al., 2009; Scott and Blanchard, 2009; Blanchard et al., 2010; Li et al., 2009; Nguyen et al., 2011). One of the theoretical milestones of PU learning is Elkan and Noto (2008) and there are subsequent researches called unbiased PU learning (du Plessis and Sugiyama, 2014; du Plessis et al., 2015), where the classification risk is estimated in an unbiased manner only from PU data. We consider the case-control scenario (Ward et al., 2009; Elkan and Noto, 2008), where positive data are obtained separately from unlabeled data and unlabeled data is sampled from the whole population. Under this setting, the true class-prior π p(y 1) in unlabeled data is needed for the formulation of unbiased PU learning.

A probability density function (pdf) encodes the entire stochastic knowledge about data distribution, where data may represent stochastic observations in robotics, transition state pairs in reinforcement learning or any other empirically acquired modality. Inferring data pdf is of prime importance, allowing to analyze various model hypotheses and perform smart decision making. However, most density estimation techniques are limited in their representation expressiveness to specific kernel type or predetermined distribution family, and have other restrictions. For example, kernel density estimation (KDE) methods require meticulous parameter search and are extremely slow at querying new points. In this paper we present a novel non-parametric density estimation approach, DeepPDF, that uses a neural network to approximate a target pdf given samples from thereof. Such a representation provides high inference accuracy for a wide range of target pdfs using a relatively simple network structure, making our method highly statistically robust. This is done via a new stochastic optimization algorithm, \emph{Probabilistic Surface Optimization} (PSO), that turns to advantage the stochastic nature of sample points in order to force network output to be identical to the output of a target pdf. Once trained, query point evaluation can be efficiently done in DeepPDF by a simple network forward pass, with linear complexity in the number of query points. Moreover, the PSO algorithm is capable of inferring the frequency of data samples and may also be used in other statistical tasks such as conditional estimation and distribution transformation. We compare the derived approach with KDE methods showing its superior performance and accuracy.