Most generative models for clustering implicitly assume that the number of data points in each cluster grows linearly with the total number of data points. Finite mixture models, Dirichlet process mixture models, and Pitman--Yor process mixture models make this assumption, as do all other infinitely exchangeable clustering models. However, for some applications, this assumption is inappropriate. For example, when performing entity resolution, the size of each cluster should be unrelated to the size of the data set, and each cluster should contain a negligible fraction of the total number of data points. These applications require models that yield clusters whose sizes grow sublinearly with the size of the data set. We address this requirement by defining the microclustering property and introducing a new class of models that can exhibit this property. We compare models within this class to two commonly used clustering models using four entity-resolution data sets.

Recurrent neural networks are powerful models for processing sequential data, but they are generally plagued by vanishing and exploding gradient problems. Unitary recurrent neural networks (uRNNs), which use unitary recurrence matrices, have recently been proposed as a means to avoid these issues. However, in previous experiments, the recurrence matrices were restricted to be a product of parameterized unitary matrices, and an open question remains: when does such a parameterization fail to represent all unitary matrices, and how does this restricted representational capacity limit what can be learned? To address this question, we propose full-capacity uRNNs that optimize their recurrence matrix over all unitary matrices, leading to significantly improved performance over uRNNs that use a restricted-capacity recurrence matrix. Our contribution consists of two main components. First, we provide a theoretical argument to determine if a unitary parameterization has restricted capacity. Using this argument, we show that a recently proposed unitary parameterization has restricted capacity for hidden state dimension greater than 7. Second, we show how a complete, full-capacity unitary recurrence matrix can be optimized over the differentiable manifold of unitary matrices. The resulting multiplicative gradient step is very simple and does not require gradient clipping or learning rate adaptation. We confirm the utility of our claims by empirically evaluating our new full-capacity uRNNs on both synthetic and natural data, achieving superior performance compared to both LSTMs and the original restricted-capacity uRNNs.

Abstract--Usually, complex-valued RKHS are presented as an straightforward application of the real-valued case. In this paper we prove that this procedure yields a limited solution for regression. We show that another kernel, here denoted as pseudo-kernel, is needed to learn any function in complex-valued fields. Accordingly, we derive a novel RKHS to include it, the widely RKHS (WRKHS). When the pseudo-kernel cancels, WRKHS reduces to complex-valued RKHS of previous approaches. We address the kernel and pseudo-kernel design, paying attention to the kernel and the pseudo-kernel being complex-valued. In the experiments included we report remarkable improvements in simple scenarios where real a imaginary parts have different similitude relations for given inputs or cases where real and imaginary parts are correlated. In the context of these novel results we revisit the problem of nonlinear channel equalization, to show that the WRKHS helps to design more efficient solutions. OMPLEX-V ALUED signal processing is of fundamental interest. Its main benefit is the availability of processing the real and imaginary parts as a single signal.

Unavoidable dead-ends are common in many probabilistic planning problems, e.g. when actions may fail or when operating under resource constraints. An important objective in such settings is MaxProb, determining the maximal probability with which the goal can be reached, and a policy achieving that probability. Yet algorithms for MaxProb probabilistic planning are severely underexplored, to the extent that there is scant evidence of what the empirical state of the art actually is. We close this gap with a comprehensive empirical analysis. We design and explore a large space of heuristic search algorithms, systematizing known algorithms and contributing several new algorithm variants. We consider MaxProb, as well as weaker objectives that we baptize AtLeastProb (requiring to achieve a given goal probabilty threshold) and ApproxProb (requiring to compute the maximum goal probability up to a given accuracy). We explore both the general case where there may be 0-reward cycles, and the practically relevant special case of acyclic planning, such as planning with a limited action-cost budget. We design suitable termination criteria, search algorithm variants, dead-end pruning methods using classical planning heuristics, and node selection strategies. We design a benchmark suite comprising more than 1000 instances adapted from the IPPC, resource-constrained planning, and simulated penetration testing. Our evaluation clarifies the state of the art, characterizes the behavior of a wide range of heuristic search algorithms, and demonstrates significant benefits of our new algorithm variants.

Who here remembers taking computer programming in school? Whether you learned programming by punching holes in a never ending series of cards, or by writing simple DOS or other computer language commands, the fact remained that computers needed an incredibly precise set of instructions to accomplish a task. The more complicated the task, the more complicated your instructions had to be. Machine learning is inherently different. Rather than telling a computer exactly how to solve a problem, the programmer instead tells it how to go about learning to solve the problem for itself.

On 26 October 2016, UBS held its second UBS Future of Finance Forum, this time in Zurich. The conference saw leaders and experts from the financial industry, fintechs, academia and regulators come together to discuss the future of Intelligent Automation and start to build a common understanding of what a successful approach would look like. We discussed evolving client preferences, what constitutes a'good' intelligent agent and how AI will impact our business. We sounded the drivers for automation and attempted to set its ethical boundaries, investigate the optimal human / co-bot collaboration, control risks and manage the new workforce. We debated sensible requirements from regulator and bank perspective and how to identify and manage liability.

Jason Mars is an African-American professor of computer science who also runs a tech start-up. When his company's artificially intelligent smartphone app talks, he said, it sounds "like a helpful, young Caucasian female." "There's a kind of pressure to conform to the prejudices of the world" when you are trying to make a consumer hit, he said. "It would be interesting to have a black guy talk, but we don't want to create friction, either. First we need to sell products." Mr. Mars's start-up is part of a growing high-tech field called conversational computing.

Police drone footage shows extent of the damage at the Royal Clarence Hotel in Exeter, Devon, after it was gutted by fire.

A basketball fan of my close acquaintance woke up Wednesday morning and, upon learning the outcome of the first games of the NBA season, announced that "The Warriors suck." Can we answer this question? To put it more precisely, how much information is supplied by that first-game-of-season blowout? Speaking Bayesianly, who much should we adjust our expectation that the Splashies will dominate this year? This is an interesting question in its own right but also is an example of something I've been thinking about regarding base-rate fallacy and the rate of integration of information over time, and it relates to some of our favorite topics such as odds for presidential vote, Brexit, Leicester City, etc.

Amazon has crowned the latest champion in its robotic picking challenge -- an annual competition that looks for robots that could one day work in the company's warehouses. It's basically American Idol, but for robotic arms that can grab items off a shelf and put them back again. Competitors are asked to handle a range of products, from toiletries to clothes, and then scored on speed and accuracy in stocking shelves. This year's contest was won by a joint team from the TU Delft Robotics Institute in the Netherlands and the company Delft Robotics (both named after the city of Delft). The team's robot managed to pick items from a mock Amazon warehouse shelf at a speed of around 100 an hour, reports TechRepublic, with a failure rate of 16.7 percent.