Google may be pitching its artificial intelligence and machine learning tools for a new military project. The search giant has been winding down its involvement with the Pentagon's controversial Project Maven, but Google's Cloud team is now talking with members of the US special operations community, according to Defense One. A document distributed last month at the Special Operations Forces Industry Conference (SOFIC) in Tampa, Florida described how Google Cloud's AI tools could be used by some special operations forces. Google has been winding down its involvement with the Pentagon's controversial Project Maven, but its Cloud team is now talking with the US special operations community The US Special Operations Forces include specialized units of the military like the Green Berets and the Navy SEALs, among others. 'As part of the Special Operations mission to turn captured enemy material into actionable intelligence, Commands are tasked with collection, exploitation, and dissemination of unclassified material to include documents, images, audio, and video,' according to the document, which was obtained by Defense One. It also notes how Google Cloud's machine learning application programming interfaces (APIs), storage resources and other technologies can help'accelerate exploitation of valuable unclassified intelligence material.'

High dimensional structured data enriched model describes groups of observations by shared and per-group individual parameters, each with its own structure such as sparsity or group sparsity. In this paper, we consider the general form of data enrichment where data comes in a fixed but arbitrary number of groups G. Any convex function, e.g., norms, can characterize the structure of both shared and individual parameters. We propose an estimator for high dimensional data enriched model and provide conditions under which it consistently estimates both shared and individual parameters. We also delineate sample complexity of the estimator and present high probability non-asymptotic bound on estimation error of all parameters. Interestingly the sample complexity of our estimator translates to conditions on both per-group sample sizes and the total number of samples. We propose an iterative estimation algorithm with linear convergence rate and supplement our theoretical analysis with synthetic and real experimental results. Particularly, we show the predictive power of data-enriched model along with its interpretable results in anticancer drug sensitivity analysis.

A long standing problem in visual object categorization is the ability of algorithms to generalize across different testing conditions. The problem has been formalized as a covariate shift among the probability distributions generating the training data (source) and the test data (target) and several domain adaptation methods have been proposed to address this issue. While these approaches have considered the single source-single target scenario, it is plausible to have multiple sources and require adaptation to any possible target domain. This last scenario, named Domain Generalization (DG), is the focus of our work. Differently from previous DG methods which learn domain invariant representations from source data, we design a deep network with multiple domain-specific classifiers, each associated to a source domain. At test time we estimate the probabilities that a target sample belongs to each source domain and exploit them to optimally fuse the classifiers predictions. To further improve the generalization ability of our model, we also introduced a domain agnostic component supporting the final classifier. Experiments on two public benchmarks demonstrate the power of our approach.

This paper deals with robust regression and subspace estimation and more precisely with the problem of minimizing a saturated loss function. In particular, we focus on computational complexity issues and show that an exact algorithm with polynomial time-complexity with respect to the number of data can be devised for robust regression and subspace estimation. This result is obtained by adopting a classification point of view and relating the problems to the search for a linear model that can approximate the maximal number of points with a given error. Approximate variants of the algorithms based on ramdom sampling are also discussed and experiments show that it offers an accuracy gain over the traditional RANSAC for a similar algorithmic simplicity.

Gibbs sampling is a Markov chain Monte Carlo method that is one of the most widespread techniques used with graphical models [7]. Gibbs sampling is an iterative method that repeatedly resamples a variable in the model from its conditional distribution, a process that is guaranteed to converge asymptotically to the desired distribution. Since these updates are typically simple and fast to run, Gibbs sampling can be applied to a variety of problems, and has been used for inference on large-scale graphical models in many systems [11, 13, 14, 19, 20, 21]. Unfortunately, for large graphical models with many factors, the computational cost of running an iteration of Gibbs sampling can become prohibitive. Even though Gibbs sampling is a graph-local algorithm, in the sense that each update only needs to reference data associated with a local neighborhood of the factor graph, as graphs become large and highly connected, even these local neighborhoods can become huge.

The problem of frequent pattern mining has been studied quite extensively for various types of data, including sets, sequences, and graphs. Somewhat surprisingly, another important type of data, namely rank data, has received very little attention in data mining so far. In this paper, we therefore addresses the problem of mining rank data, that is, data in the form of rankings (total orders) of an underlying set of items. More specifically, two types of patterns are considered, namely frequent rankings and dependencies between such rankings in the form of association rules. Algorithms for mining frequent rankings and frequent closed rankings are proposed and tested experimentally, using both synthetic and real data.

While active learning offers potential cost savings, the actual data efficiency---the reduction in amount of labeled data needed to obtain the same error rate---observed in practice is mixed. This paper poses a basic question: when is active learning actually helpful? We provide an answer for logistic regression with the popular active learning algorithm, uncertainty sampling. Empirically, on 21 datasets from OpenML, we find a strong inverse correlation between data efficiency and the error rate of the final classifier. Theoretically, we show that for a variant of uncertainty sampling, the asymptotic data efficiency is within a constant factor of the inverse error rate of the limiting classifier.

While statistics and machine learning offers numerous methods for ensuring generalization, these methods often fail in the presence of adaptivity---the common practice in which the choice of analysis depends on previous interactions with the same dataset. A recent line of work has introduced powerful, general purpose algorithms that ensure post hoc generalization (also called robust or post-selection generalization), which says that, given the output of the algorithm, it is hard to find any statistic for which the data differs significantly from the population it came from. In this work we show several limitations on the power of algorithms satisfying post hoc generalization. First, we show a tight lower bound on the error of any algorithm that satisfies post hoc generalization and answers adaptively chosen statistical queries, showing a strong barrier to progress in post selection data analysis. Second, we show that post hoc generalization is not closed under composition, despite many examples of such algorithms exhibiting strong composition properties.

We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generative model bringing together: an encoder which can encode an arbitrary set of observed pixels, latent variables which are trained to represent disentangled factors of variations, and a bidirectional PixelCNN model. We experimentally demonstrate that our method can generate plausible inpainting results matching the user-specified semantics, but is still coherent with observed pixels. We justify our choices of architecture and training regime through more experiments.

An artificial agent for financial risk and returns' prediction is built with a modular cognitive system comprised of interconnected recurrent neural networks, such that the agent learns to predict the financial returns, and learns to predict the squared deviation around these predicted returns. These two expectations are used to build a volatility-sensitive interval prediction for financial returns, which is evaluated on three major financial indices and shown to be able to predict financial returns with higher than 80% success rate in interval prediction in both training and testing, raising into question the Efficient Market Hypothesis. The agent is introduced as an example of a class of artificial intelligent systems that are equipped with a Modular Networked Learning cognitive system, defined as an integrated networked system of machine learning modules, where each module constitutes a functional unit that is trained for a given specific task that solves a subproblem of a complex main problem expressed as a network of linked subproblems. In the case of neural networks, these systems function as a form of an "artificial brain", where each module is like a specialized brain region comprised of a neural network with a specific architecture.