Machine learning algorithms have difficulties to generalize over a small set of examples. Humans can perform such a task by exploiting vast amount of background knowledge they possess. One method for enhancing learning algorithms with external knowledge is through feature generation. In this paper, we introduce a new algorithm for generating features based on a collection of auxiliary datasets. We assume that, in addition to the training set, we have access to additional datasets. Unlike the transfer learning setup, we do not assume that the auxiliary datasets represent learning tasks that are similar to our original one. The algorithm finds features that are common to the training set and the auxiliary datasets. Based on these features and examples from the auxiliary datasets, it induces predictors for new features from the auxiliary datasets. The induced predictors are then added to the original training set as generated features. Our method was tested on a variety of learning tasks, including text classification and medical prediction, and showed a significant improvement over using just the given features.

Machine learning models are vulnerable to adversarial perturbations, that when added to an input, can cause high confidence misclassifications. The adversarial learning research community has made remarkable progress in the understanding of the root causes of adversarial perturbations. However, most problems that one may consider important to solve for the deployment of machine learning in safety critical tasks involve high dimensional complex manifolds that are difficult to characterize and study. It is common to develop adversarially robust learning theory on simple problems, in the hope that insights will transfer to `real world datasets'. In this work, we discuss a setting where this approach fails. In particular, we show with a linear classifier, it is always possible to solve a binary classification problem on Gaussian data under arbitrary levels of adversarial corruption during training, and that this property is not observed with non-linear classifiers on the CIFAR-10 dataset.

Plackett-Luce model (PL) is one of the most popular models for preference learning. In this paper, we consider PL with features and its mixture models, where each alternative has a vector of features, possibly different across agents. Such models significantly generalize the standard PL, but are not as well investigated in the literature. We extend mixtures of PLs with features to models that generate top-$l$ and characterize their identifiability. We further prove that when PL with features is identifiable, its MLE is consistent with a strictly concave objective function under mild assumptions. Our experiments on synthetic data demonstrate the effectiveness of MLE on PL with features with tradeoffs between statistical efficiency and computational efficiency when $l$ takes different values. For mixtures of PL with features, we show that an EM algorithm outperforms MLE in MSE and runtime.

We propose a probabilistic kernel approach for preferential learning from pairwise duelling data using Gaussian Processes. Different from previous methods, we do not impose a total order on the item space, hence can capture more expressive latent preferential structures such as inconsistent preferences and clusters of comparable items. Furthermore, we prove the universality of the proposed kernels, i.e. that the corresponding reproducing kernel Hilbert Space (RKHS) is dense in the space of skew-symmetric preference functions. To conclude the paper, we provide an extensive set of numerical experiments on simulated and real-world datasets showcasing the competitiveness of our proposed method with state-of-the-art.

Graph Convolutional Networks (GCNs) generalize the idea of deep convolutional networks to graphs, and achieve state-of-the-art results on many graph related tasks. GCNs rely on the graph structure to define an aggregation strategy where each node updates its representation by combining information from its neighbours. In this paper we formalize four levels of structural information injection, and use them to show that GCNs ignore important long-range dependencies embedded in the overall topology of a graph. Our proposal includes a novel regularization technique based on random walks with restart, called RWRReg, which encourages the network to encode long-range information into the node embeddings. RWRReg is further supported by our theoretical analysis, which demonstrates that random walks with restart empower aggregation-based strategies (i.e., the Weisfeiler-Leman algorithm) with long-range information. We conduct an extensive experimental analysis studying the change in performance of several state-of-the-art models given by the four levels of structural information injection, on both transductive and inductive tasks. The results show that the lack of long-range structural information greatly affects performance on all considered models, and that the information extracted by random walks with restart, and exploited by RWRReg, gives an average accuracy improvement of more than $5\%$ on all considered tasks.

The signature transform is a 'universal nonlinearity' on the space of continuous vector-valued paths, and has received attention for use in machine learning on time series. However, real-world temporal data is typically observed at discrete points in time, and must first be transformed into a continuous path before signature techniques can be applied. We make this step explicit by characterising it as an imputation problem, and empirically assess the impact of various imputation strategies when applying signature-based neural nets to irregular time series data. For one of these strategies, Gaussian process (GP) adapters, we propose an extension~(GP-PoM) that makes uncertainty information directly available to the subsequent classifier while at the same time preventing costly Monte-Carlo (MC) sampling. In our experiments, we find that the choice of imputation drastically affects shallow signature models, whereas deeper architectures are more robust. Next, we observe that uncertainty-aware predictions (based on GP-PoM or indicator imputations) are beneficial for predictive performance, even compared to the uncertainty-aware training of conventional GP adapters. In conclusion, we have demonstrated that the path construction is indeed crucial for signature models and that our proposed strategy leads to competitive performance in general, while improving robustness of signature models in particular.

Parallelism is a ubiquitous method for accelerating machine learning algorithms. However, theoretical analysis of parallel learning is usually done in an algorithm- and protocol-specific setting, giving little insight about how changes in the structure of communication could affect convergence. In this paper we propose MixML, a general framework for analyzing convergence of weakly consistent parallel machine learning. Our framework includes: (1) a unified way of modeling the communication process among parallel workers; (2) a new parameter, the mixing time tmix, that quantifies how the communication process affects convergence; and (3) a principled way of converting a convergence proof for a sequential algorithm into one for a parallel version that depends only on tmix. We show MixML recovers and improves on known convergence bounds for asynchronous and/or decentralized versions of many algorithms, includingSGD and AMSGrad. Our experiments substantiate the theory and show the dependency of convergence on the underlying mixing time.

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it achieves $\tilde{O}(\sqrt{H^2SAT})$ regret where $T = KH$ and $K$ is the number of episodes to play. Our regret bound improves upon the results of [Jin et al., 2018] and matches the best known model-based algorithms as well as the information theoretic lower bound up to logarithmic factors. We also show that UCB-Advantage achieves low local switching cost and applies to concurrent reinforcement learning, improving upon the recent results of [Bai et al., 2019].

In studying robots and planning problems, a basic question is what is the minimal information a robot must obtain to guarantee task completion. Erdmann's theory of action-based sensors is a classical approach to characterizing fundamental information requirements. That approach uses a plan to derive a type of virtual sensor which prescribes actions that make progress toward a goal. We show that the established theory is incomplete: the previous method for obtaining such sensors, using backchained plans, overlooks some sensors. Furthermore, there are plans, that are guaranteed to achieve goals, where the existing methods are unable to provide any action-based sensor. We identify the underlying feature common to all such plans. Then, we show how to produce action-based sensors even for plans where the existing treatment is inadequate, although for these cases they have no single canonical sensor. Consequently, the approach is generalized to produce sets of sensors. Finally, we show also that this is a complete characterization of action-based sensors for planning problems and discuss how an action-based sensor translates into the traditional conception of a sensor.

The next time you load up the latest "Call of Duty" video game, you will likely notice a new message from its developers: Black Lives Matter. Infinity Ward, the development studio that makes "Call of Duty," added a message on screen that appears right before the game starts condemning racism and social injustice. "Our community is hurting," reads a portion the message. "The systemic inequalities our community experiences are once again center stage. Call of Duty and Infinity Ward stand for equality and inclusion. We stand against the racism and injustice our Black community endures. Until change happens and Black Lives Matter, we will never truly be the community we strive to be." "Call of Duty," published by Activision, is the latest example of companies and brands using their platforms to speak out on social issues.