Winners Announced for the Zillow Prize For Spectrum's January issue, I wrote about the Zillow Prize competition, in which nearly 4,000 teams were pitted against one another in a quest to come up with a computerized algorithm or machine-learning system that could predict the future sale price of homes. Real-estate giant Zillow organized the competition in hopes of using what it learned from these teams to improve its own system of predicting home prices, something the company calls the "Zestimate." And today, Zillow has announced a winner: a team made up of Chahhou Mohamed of Morocco, Jordan Meyer of the United States, and Nima Shahbazi of Canada, whose predictions bettered the Zestimate by about 13 percent. Stan Humphries, chief analytics officer for the Zillow Group, in Seattle, says that he and his colleagues have learned an enormous amount from the winning team and others in the competition--thousands of people working for two years on the problem: "That's a huge help," says Humphries. Although he couldn't be too specific, Humphries shared that one area of insight was "how you combine various models in an ensemble approach."

We consider the closeness testing (or two-sample testing) problem in the Poisson vector model - which is known to be asymptotically equivalent to the model of multinomial distributions. The goal is to distinguish whether two data samples are drawn from the same unspecified distribution, or whether their respective distributions are separated in $L_1$-norm. In this paper, we focus on adapting the rate to the shape of the underlying distributions, i.e. we consider a local minimax setting. We provide, to the best of our knowledge, the first local minimax rate for the separation distance up to logarithmic factors, together with a test that achieves it. In view of the rate, closeness testing turns out to be substantially harder than the related one-sample testing problem over a wide range of cases.

This paper focuses on Bayesian Optimization - typically considered with continuous inputs - for discrete search input spaces, including integer, categorical or graph structured input variables. In Gaussian process-based Bayesian Optimization a problem arises, as it is not straightforward to define a proper kernel on discrete input structures, where no natural notion of smoothness or similarity could be provided. We propose COMBO, a method that represents values of discrete variables as vertices of a graph and then use the diffusion kernel on that graph. As the graph size explodes with the number of categorical variables and categories, we propose the graph Cartesian product to decompose the graph into smaller sub-graphs, enabling kernel computation in linear time with respect to the number of input variables. Moreover, in our formulation we learn a scale parameter per subgraph. In empirical studies on four discrete optimization problems we demonstrate that our method is on par or outperforms the state-of-the-art in discrete Bayesian optimization.

The term neural networks refers to networks of neurons in the mammalian brain. Neurons are its fundamental units of computation. In the brain they are connected together in networks to process data. This can be a very complex task, and the dynamics of neural networks in the mammalian brain in response to external stimuli can therefore be quite intricate. Inputs and outputs of each neuron vary as functions of time, in the form of so-called spike trains, but also the network itself changes. We learn and improve our data-processing capacities by establishing reconnections between neurons. Neural-networkalgorithms are inspired by the architecture and the dynamics of networks of neurons in the brain. Yet the algorithms use neuron models that are highly simplified, compared with real neurons. Nevertheless, the fundamental principle is the same: artificial neural networks learn by reconnection.

Despite the progress within the last decades, weather forecasting is still a challenging and computationally expensive task. Current satellite-based approaches to predict thunderstorms are usually based on the analysis of the observed brightness temperatures in different spectral channels and emit a warning if a critical threshold is reached. Recent progress in data science however demonstrates that machine learning can be successfully applied to many research fields in science, especially in areas dealing with large datasets. We therefore present a new approach to the problem of predicting thunderstorms based on machine learning. The core idea of our work is to use the error of two-dimensional optical flow algorithms applied to images of meteorological satellites as a feature for machine learning models. We interpret that optical flow error as an indication of convection potentially leading to thunderstorms and lightning. To factor in spatial proximity we use various manual convolution steps. We also consider effects such as the time of day or the geographic location. We train different tree classifier models as well as a neural network to predict lightning within the next few hours (called nowcasting in meteorology) based on these features. In our evaluation section we compare the predictive power of the different models and the impact of different features on the classification result. Our results show a high accuracy of 96% for predictions over the next 15 minutes which slightly decreases with increasing forecast period but still remains above 83% for forecasts of up to five hours. The high false positive rate of nearly 6% however needs further investigation to allow for an operational use of our approach.

You wake up one morning to discover that your child is ill: His forehead feels hot to the touch, and his rapid breathing has a wheezing sound. You live in Malawi, where your health care options are few. When the local clinic opens, you wait for your turn with the solitary clinic worker. She's not a doctor, but she's been trained to identify and handle routine problems. She puts on a stethoscope and presses its chest piece against your son's front and back to carefully listen to his lungs.

CAPE TOWN – Microsoft South Africa has launched a new initiative called Make Your Wish aimed to help individuals and organisations share their ideas on how artificial intelligence (AI) can bring about changes in the world. Microsoft SA said in a statement: "Make Your Wish will act as a platform to bring ideas and imaginations together from bright minds on implementing Artificial Intelligence and how it could help improve lives – and empower people and organizations to achieve more."

We consider the problem of designing an artificial agent capable of interacting with humans in collaborative dialogue to produce creative, engaging narratives. In this task, the goal is to establish universe details, and to collaborate on an interesting story in that universe, through a series of natural dialogue exchanges. Our model can augment any probabilistic conversational agent by allowing it to reason about universe information established and what potential next utterances might reveal. Ideally, with each utterance, agents would reveal just enough information to add specificity and reduce ambiguity without limiting the conversation. We empirically show that our model allows control over the rate at which the agent reveals information and that doing so significantly improves accuracy in predicting the next line of dialogues from movies. We close with a case-study with four professional theatre performers, who preferred interactions with our model-augmented agent over an unaugmented agent.

We describe the setting and results of the ConvAI2 NeurIPS competition that aims to further the state-of-the-art in open-domain chatbots. Some key takeaways from the competition are: (i) pretrained Transformer variants are currently the best performing models on this task, (ii) but to improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations) in terms of repetition, consistency and balance of dialogue acts (e.g. The Conversational Intelligence Challenge aims at finding approaches to creating highquality dialogue agents capable of meaningful open domain conversation. Today, the progress in the field is significantly hampered by the absence of established benchmark tasks for non-goal-oriented dialogue systems (chatbots) and solid evaluation criteria for automatic assessment of dialogue quality. The aim of this competition was therefore to establish a concrete scenario for testing chatbots that aim to engage humans, and become a standard evaluation tool in order to make such systems directly comparable, including open source datasets, evaluation code (both automatic evaluations and code to run the human evaluation on Mechanical Turk), model baselines and the winning model itself. Taking into account the results of the previous edition, this year we improved the task, the evaluation process, and the human conversationalists' experience. We did this in part by making the setup simpler for the competitors, and in part by making the conversations more engaging for humans. We provided a dataset from the beginning, Persona-Chat, whose training set consists of conversations between crowdworkers who were randomly paired and asked to act the part of a given provided persona (randomly assigned, and created by another set of crowdworkers). The paired workers were asked to chat naturally and to get to know each other during the conversation. This produces interesting and engaging conversations that learning agents can try to mimic.

We study a loss function that is the negative log-likelihood of the model. We analyse the number of local minima at a fixed distance from the signal/spike with the Kac-Rice formula, and locate trivialization of the landscape at large signal-to-noise ratios. We evaluate in a closed form the performance of a gradient flow algorithm using integro-differential PDEs as developed in physics of disordered systems for the Langevin dynamics. We analyze the performance of an approximate message passing algorithm estimating the maximum likelihood configuration via its state evolution. We conclude by comparing the above results: while we observe a drastic slow down of the gradient flow dynamics even in the region where the landscape is trivial, both the analyzed algorithms are shown to perform well even in the part of the region of parameters where spurious local minima are present.