This paper explores the adaptively (active) PAC (probably approximately correct) top-$k$ ranking and total ranking from $l$-wise ($l\geq 2$) comparisons under the popular multinomial logit (MNL) model. By adaptively choosing sets to query and observing the noisy output about the most favored item of each query, we want to design ranking algorithms that recover the top-$k$ or total ranking using as few queries as possible. For the PAC top-$k$ ranking problem, we prove a lower bound on the sample complexity (aka number of queries), and propose an algorithm that is sample complexity optimal up to a $O(\log(k+l)/\log{k})$ factor. When $l=2$ (i.e., pairwise) or $l=O(poly(k))$, the algorithm matches the lower bound. For the PAC total ranking problem, we prove a lower bound, and propose an algorithm that matches the lower bound. When $l=2$, this model reduces to the popular Plackett-Luce (PL) model, and our results still outperform the state-of-the-art theoretically and numerically. We also run comparisons of our algorithms with the state-of-the-art on synthesized data as well as real-world data, and demonstrate the improvement on sample complexity numerically.

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional distributions between the domains, while simultaneously learning to sample from the marginals of each individual domain. The proposed framework consists of multiple generators and a single softmax-based critic, all jointly trained via adversarial learning. From a simple noise source, the proposed framework allows synthesis of draws from the marginals, conditional draws given observations from a subset of random variables, or complete draws from the full joint distribution. Most examples considered are for joint analysis of two domains, with examples for three domains also presented.

Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. BB-FDR learns a series of black box predictive models to boost power and control the false discovery rate (FDR) at two stages of study analysis. In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, a separate black box model of each covariate is used to select features that have significant predictive power across all experiments. In benchmarks, BB-FDR outperforms competing state-of-the-art methods in both stages of analysis. We apply BB-FDR to two real studies on cancer drug efficacy. For both studies, BB-FDR increases the proportion of significant outcomes discovered and selects variables that reveal key genomic drivers of drug sensitivity and resistance in cancer.

Neural message passing on molecular graphs is one of the most promising methods for predicting formation energy and other properties of molecules and materials. In this work we extend the neural message passing model with an edge update network which allows the information exchanged between atoms to depend on the hidden state of the receiving atom. We benchmark the proposed model on three publicly available datasets (QM9, The Materials Project and OQMD) and show that the proposed model yields superior prediction of formation energies and other properties on all three datasets in comparison with the best published results. Furthermore we investigate different methods for constructing the graph used to represent crystalline structures and we find that using a graph based on K-nearest neighbors achieves better prediction accuracy than using maximum distance cutoff or the Voronoi tessellation graph.

In machine learning, novelty detection is the task of identifying novel unseen data. During training, only samples from the normal class are available. Test samples are classified as normal or abnormal by assignment of a novelty score. Here we propose novelty detection methods based on training variational autoencoders (VAEs) on normal data. Since abnormal samples are not used during training, we define novelty metrics based on the (partially complementary) assumptions that the VAE is less capable of reconstructing abnormal samples well; that abnormal samples more strongly violate the VAE regularizer; and that abnormal samples differ from normal samples not only in input-feature space, but also in the VAE latent space and VAE output. These approaches, combined with various possibilities of using (e.g.~sampling) the probabilistic VAE to obtain scalar novelty scores, yield a large family of methods. We apply these methods to magnetic resonance imaging, namely to the detection of diffusion-space (\mbox{q-space}) abnormalities in diffusion MRI scans of multiple sclerosis patients, i.e.~to detect multiple sclerosis lesions without using any lesion labels for training. Many of our methods outperform previously proposed q-space novelty detection methods.

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from another network, pre-trained on a different task. While this approach can only approximate the ideal curriculum, we observe empirically similar behavior to the one predicted by the theory, namely, a significant boost in convergence speed at the beginning of training. When the task is made more difficult, improvement in generalization performance is also observed. Finally, curriculum learning exhibits robustness against unfavorable conditions such as excessive regularization.

SAN FRANCISCO – Google will not allow its artificial intelligence software to be used in weapons or unreasonable surveillance efforts, the Alphabet Inc. unit said Thursday in standards for its business decisions in the nascent field. The new restrictions could help Google management defuse months of protest by thousands of employees against the company's work with the U.S. military to identify objects in drone video. Google will pursue other government contracts, including around cybersecurity, military recruitment and search and rescue, Chief Executive Sundar Pichai said in a blog post Thursday. "We want to be clear that while we are not developing AI for use in weapons, we will continue our work with governments and the military in many other areas," he said. Breakthroughs in the cost and performance of advanced computers have begun to carry AI from research labs into industries such as defense and health.

If the robotics world had a celebrity it would be Spot Mini of Boston Dynamics. Last month at the Robotics Summit in Boston the mechanical dog strutted onto the floor of the Westin Hotel trailed by hundreds of flickering iPhones. Marc Raibert first unveiled his metal menaagerie almost a decade ago with a video of Big Dog. Today, Mini is the fulfillment of his mission in a sleeker, smarter, and environmentally friendlier robo-canine package than its gas-burning ancestor. Since the early 1990s, machines have relied on rechargeable lithium ion batteries for power.

The government has allocated £300m in new funding to invest in AI research in a bid to make the UK a global leader in the technology. According to a press release, more than 50 businesses and organisations have contributed to the development of a £1bn deal, which was announced by business secretary Greg Clark and digital secretary Matt Hancock. The new funding builds on the commitment made in the government's modern Industrial Strategy and its AI Grand Challenge. It aims to help the UK seize the £232bn opportunity artificial intelligence offers the UK economy by 2030. Today's announcement comes after'record levels' of investment into the UK tech sector last year, and includes new deals such as: "The UK must be at the forefront of emerging technologies, pushing boundaries and harnessing innovation to change people's lives for the better. "Artificial Intelligence is at the centre of our plans to make the UK the best place in the world to start and grow a digital business.