In the coming decades, diagnostic medicine will likely change dramatically. Perhaps the most conspicuous change will be the arrival of artificial intelligence (AI) for faster and better care. AI is not pitting man against machine. It is, in fact, a way to ease the physician's burden and expand the possibilities of treatment. The administrative aspect of practicing medicine can be overwhelming, to say the least, and AI offers the chance to sort through large amounts of information quickly and accurately.

If the history of human advancement has taught us one thing it is this: genuine step-change progress does not occur because of a single technology breakthrough, but a combination of multiple complementary factors coming together at the same time. The Industrial Revolution, which began in the UK around 1760, was driven by an amalgamation of steam power, improvements in iron production and the development of the first machine tools. Similarly, the PC revolution of the early 1970's was the outcome of simultaneous advancements in micro-processing, memory storage, software programming and other factors. Now, as we enter 2018, we are at the cusp of a new revolution, one that will ultimately transform every organisation, every industry and every public service across the world. This is referring to Artificial Intelligence – or AI – and this 2018 is the year that this will start to become mainstream, to begin to impact many aspects of our lives in a truly ubiquitous and meaningful way.

We introduce SCAL, an algorithm designed to perform efficient exploration-exploitation in any unknown weakly-communicating Markov Decision Process (MDP) for which an upper bound c on the span of the optimal bias function is known. For an MDP with S states, A actions and Gamma <= S possible next states, we prove a regret bound of O(c\sqrt{Gamma SAT}), which significantly improves over existing algorithms (e.g., UCRL and PSRL), whose regret scales linearly with the MDP diameter D. In fact, the optimal bias span is finite and often much smaller than D (e.g., D=infinity in non-communicating MDPs). A similar result was originally derived by Bartlett and Tewari (2009) for REGAL.C, for which no tractable algorithm is available. In this paper, we relax the optimization problem at the core of REGAL.C, we carefully analyze its properties, and we provide the first computationally efficient algorithm to solve it. Finally, we report numerical simulations supporting our theoretical findings and showing how SCAL significantly outperforms UCRL in MDPs with large diameter and small span.

Linear least-squares regression with a "design" matrix A approximates a given matrix B via minimization of the spectral- or Frobenius-norm discrepancy ||AX-B|| over every conformingly sized matrix X. Another popular approximation is low-rank approximation via principal component analysis (PCA) -- which is essentially singular value decomposition (SVD) -- or interpolative decomposition (ID). Classically, PCA/SVD and ID operate solely with the matrix B being approximated, not supervised by any auxiliary matrix A. However, linear least-squares regression models can inform the ID, yielding regression-aware ID. As a bonus, this provides an interpretation as regression-aware PCA for a kind of canonical correlation analysis between A and B. The regression-aware decompositions effectively enable supervision to inform classical dimensionality reduction, which classically has been totally unsupervised. The regression-aware decompositions reveal the structure inherent in B that is relevant to regression against A.

Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much recent interest, and a number of fairness-enhanced classifiers and predictors have appeared in the literature. This paper seeks to study the following questions: how do these different techniques fundamentally compare to one another, and what accounts for the differences? Specifically, we seek to bring attention to many under-appreciated aspects of such fairness-enhancing interventions. Concretely, we present the results of an open benchmark we have developed that lets us compare a number of different algorithms under a variety of fairness measures, and a large number of existing datasets. We find that although different algorithms tend to prefer specific formulations of fairness preservations, many of these measures strongly correlate with one another. In addition, we find that fairness-preserving algorithms tend to be sensitive to fluctuations in dataset composition (simulated in our benchmark by varying training-test splits), indicating that fairness interventions might be more brittle than previously thought.

A problem facing many services - from search engines and news feeds to machine learning - is data summarization: how can one select a small but representative, i.e., diverse, subset from a large dataset. For instance, Google Images outputs a small subset of images from its enormous dataset given a user query. Similarly, in training a learning algorithm one may be required to choose a subset of data points to train on as training on the entire dataset may be costly. However, data summarization algorithms prevalent in the online world have been recently shown to be biased with respect to sensitive attributes such as gender, race and ethnicity. For instance, a recent study found evidence of systematic under-representation of women in search results [14]. Concretely, the above work studied the output of Google Images for various search terms involving occupations and found, e.g., that for the search term "CEO", the percentage of women in top 100 results was 11%, significantly lower than the ground truth of 27%. Through studies on human subjects, they also found that such misrepresentations have the power to influence people's perception about reality. Beyond humans, since data summaries are used to train algorithms, there is a danger that these biases in the data might be passed on to the algorithms that use them; a phenomena that is being revealed more and more in automated data-driven processes in education, recruitment, banking, and judiciary systems, see [22]. A robust and widely deployed method for data summarization is to associate a diversity score to each subset and select a subset with probability proportional to this score; see [13].

Structured prediction requires searching over a combinatorial number of structures. To tackle it, we introduce SparseMAP, a new method for sparse structured inference, together with corresponding loss functions. SparseMAP inference is able to automatically select only a few global structures: it is situated between MAP inference, which picks a single structure, and marginal inference, which assigns probability mass to all structures, including implausible ones. Importantly, SparseMAP can be computed using only calls to a MAP oracle, hence it is applicable even to problems where marginal inference is intractable, such as linear assignment. Moreover, thanks to the solution sparsity, gradient backpropagation is efficient regardless of the structure. SparseMAP thus enables us to augment deep neural networks with generic and sparse structured hidden layers. Experiments in dependency parsing and natural language inference reveal competitive accuracy, improved interpretability, and the ability to capture natural language ambiguities, which is attractive for pipeline systems.

Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. As the representation learned captures the variation in the environment generated by agents, this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research.

Healthcare companies must submit pharmaceutical drugs or medical devices to regulatory bodies before marketing new technology. Regulatory bodies frequently require transparent and interpretable computational modelling to justify a new healthcare technology, but researchers may have several competing models for a biological system and too little data to discriminate between the models. In design of experiments for model discrimination, the goal is to design maximally informative physical experiments in order to discriminate between rival predictive models. Prior work has focused either on analytical approaches, which cannot manage all functions, or on data-driven approaches, which may have computational difficulties or lack interpretable marginal predictive distributions. We develop a methodology introducing Gaussian process surrogates in lieu of the original mechanistic models. We thereby extend existing design and model discrimination methods developed for analytical models to cases of non-analytical models in a computationally efficient manner.

We study safe screening for metric learning. Distance metric learning can optimize a metric over a set of triplets, each one of which is defined by a pair of same class instances and an instance in a different class. However, the number of possible triplets is quite huge even for a small dataset. Our safe triplet screening identifies triplets which can be safely removed from the optimization problem without losing the optimality. Compared with existing safe screening studies, triplet screening is particularly significant because of (1) the huge number of possible triplets, and (2) the semi-definite constraint in the optimization. We derive several variants of screening rules, and analyze their relationships. Numerical experiments on benchmark datasets demonstrate the effectiveness of safe triplet screening.