Som e notable recent advances include proposals based on the ridge estimate ( B uhlmann, 2013; Nickl and van de Geer, 2013), on the lasso estimate ( Van de Geer et al., 2014; Zhang and Zhang, 2014), score and orthogonal moments methods ( Belloni et al., 2014a; Goeman et al., 2006), as well as combinations thereof (see for example Belloni et al. ( 2014b); Javanmard and Montanari ( 2014)). Although this line of work has led to many promising methods, the literature, however, does not provide an answer as to how these meth ods should be adapted for the lack of sparse structures in the underlying mod els. First, there is no guidance on how to check whether a model is sparse or no t in high-dimensional settings; the majority of methods construct co nfidence intervals under a set of assumptions describing how sparse the underlyin g model is. The process of developing algorithms that detect model sparsity is still fairly "unattainable", therefore in practice effectively rendering a prior i belief in the sparsity. Second, no comprehensive answer is able to confirm or de ny the ability to perform a hypothesis test (or to construct optimal confidenc e intervals) with formal guarantees that do not rely on model sparsity.

Online communities provide a unique way for individuals to access information from those in similar circumstances, which can be critical for health conditions that require daily and personalized management. As these groups and topics often arise organically, identifying the types of topics discussed is necessary to understand their needs. As well, these communities and people in them can be quite diverse, and existing community detection methods have not been extended towards evaluating these heterogeneities. This has been limited as community detection methodologies have not focused on community detection based on semantic relations between textual features of the user-generated content. Thus here we develop an approach, NeuroCom, that optimally finds dense groups of users as communities in a latent space inferred by neural representation of published contents of users. By embedding of words and messages, we show that NeuroCom demonstrates improved clustering and identifies more nuanced discussion topics in contrast to other common unsupervised learning approaches.

Obtaining deep networks that are robust against adversarial examples and generalize well is an open problem. A recent hypothesis even states that both robust and accurate models are impossible, i.e., adversarial robustness and generalization are conflicting goals. In an effort to clarify the relationship between robustness and generalization, we assume an underlying, low-dimensional data manifold and show that: 1. regular adversarial examples leave the manifold; 2. adversarial examples constrained to the manifold, i.e., on-manifold adversarial examples, exist; 3. on-manifold adversarial examples are generalization errors, and on-manifold adversarial training boosts generalization; 4. and regular robustness is independent of generalization. These assumptions imply that both robust and accurate models are possible. However, different models (architectures, training strategies etc.) can exhibit different robustness and generalization characteristics. To confirm our claims, we present extensive experiments on synthetic data (with access to the true manifold) as well as on EMNIST, Fashion-MNIST and CelebA.

Given a set of observations generated by an optimization process, the goal of inverse optimization is to determine likely parameters of that process. We cast inverse optimization as a form of deep learning. Our method, called deep inverse optimization, is to unroll an iterative optimization process and then use backpropagation to learn parameters that generate the observations. We demonstrate that by backpropagating through the interior point algorithm we can learn the coefficients determining the cost vector and the constraints, independently or jointly, for both non-parametric and parametric linear programs, starting from one or multiple observations. With this approach, inverse optimization can leverage concepts and algorithms from deep learning.

Although the theory of binary pattern classification is well established [1, 2], the theory of multicategory classificationis far from being complete. The research in this case addresses problems such as the sample-complexity analysis of empirical risk minimization algorithms[3], or consistency analysis of multi-class loss functions and of specific families of classifiers [4]. Another open question is the optimal dependency of guaranteed risks of multi-category classifiers on the number C of categories and the sample size m. It is all the more the case for the problems that involve a large number of classes. When the considered classifiers are margin ones that take decision based on a score per category, the dependency on the margin parameter γ also becomes relevant to the characterization of their generalization performance. If this question has been mainly studied for specific families of classifiers, be it k-nearest neighbors [5], kernel methods [6, 7] and decision trees [8], tackling it under minimal learnability assumptions remains a challenging task. This paper focuses on obtaining guaranteed risks under such assumptions.

Determining whether hypotensive patients in intensive care units (ICUs) should receive fluid bolus therapy (FBT) has been an extremely challenging task for intensive care physicians as the corresponding increase in blood pressure has been hard to predict. Our study utilized regression models and attention-based recurrent neural network (RNN) algorithms and a multi-clinical information system large-scale database to build models that can predict the successful response to FBT among hypotensive patients in ICUs. We investigated both time-aggregated modeling using logistic regression algorithms with regularization and time-series modeling using the long short term memory network (LSTM) and the gated recurrent units network (GRU) with the attention mechanism for clinical interpretability. Among all modeling strategies, the stacked LSTM with the attention mechanism yielded the most predictable model with the highest accuracy of 0.852 and area under the curve (AUC) value of 0.925. The study results may help identify hypotensive patients in ICUs who will have sufficient blood pressure recovery after FBT.

Recently, researchers have shown an increased interest in harnessing Twitter data for dynamic monitoring of traffic conditions. Bag-of-words representation is a common method in literature for tweet modeling and retrieving traffic information, yet it suffers from the curse of dimensionality and sparsity. To address these issues, our specific objective is to propose a simple and robust framework on the top of word embedding for distinguishing traffic-related tweets against non-traffic-related ones. In our proposed model, a tweet is classified as traffic-related if semantic similarity between its words and a small set of traffic keywords exceeds a threshold value. Semantic similarity between words is captured by means of word-embedding models, which is an unsupervised learning tool. The proposed model is as simple as having only one trainable parameter. The model takes advantage of outstanding merits, which are demonstrated through several evaluation steps. The state-of-the-art test accuracy for our proposed model is 95.9%. Introduction In the past decade, social media networks have received much attention among ordinary people, agencies, and research scholars. Twitter is one of the fastest-growing social media tools that enables users to post and read short messages, called tweets. By means of Twitter applications on smartphones, users are able to immediately reports events happening around them on a real-time basis. The information disseminated by millions of active users everyday generates a new version of dynamic database that contains information about various topics.

Federated learning has become an exciting direction for both research and practical training of models with user data. Although data remains decentralized in federated learning, it is common to assume that the model updates are sent in the clear from the devices to the server. Differential privacy has been proposed as a way to ensure the model remains private, but this does not address the issue that model updates can be seen on the server, and lead to leakage of user data. Local differential privacy is one of the strongest forms of privacy protection so that each individual's data is privatized. However, local differential privacy, as it is traditionally used, may prove to be too stringent of a privacy condition in many high dimensional problems, such as in distributed model fitting. We propose a new paradigm for local differential privacy by providing protections against certain adversaries. Specifically, we ensure that adversaries with limited prior information cannot reconstruct, with high probability, the original data within some prescribed tolerance. This interpretation allows us to consider larger privacy parameters. We then design (optimal) DP mechanisms in this large privacy parameter regime. In this work, we combine local privacy protections along with central differential privacy to present a practical approach to do model training privately. Further, we show that these privacy restrictions maintain utility in image classification and language models that is comparable to federated learning without these privacy restrictions.

Graphs are widely adopted for modeling complex systems, including financial, biological, and social networks. Nodes in networks usually entail attributes, such as the age or gender of users in a social network. However, real-world networks can have very large size, and nodal attributes can be unavailable to a number of nodes, e.g., due to privacy concerns. Moreover, new nodes can emerge over time, which can necessitate real-time evaluation of their nodal attributes. In this context, the present paper deals with scalable learning of nodal attributes by estimating a nodal function based on noisy observations at a subset of nodes. A multikernel-based approach is developed which is scalable to large-size networks. Unlike most existing methods that re-solve the function estimation problem over all existing nodes whenever a new node joins the network, the novel method is capable of providing real-time evaluation of the function values on newly-joining nodes without resorting to a batch solver. Interestingly, the novel scheme only relies on an encrypted version of each node's connectivity in order to learn the nodal attributes, which promotes privacy. Experiments on both synthetic and real datasets corroborate the effectiveness of the proposed methods.

Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy to train. Nevertheless, neural networks are lacking robustness and interpretability. Prototype-based vector quantization methods on the other hand are known for being robust and interpretable. For this reason, we propose techniques and strategies to merge both approaches. This contribution will particularly highlight the similarities between them and outline how to construct a prototype-based classification layer for multilayer networks. Additionally, we provide an alternative, prototype-based, approach to the classical convolution operation. Numerical results are not part of this report, instead the focus lays on establishing a strong theoretical framework. By publishing our framework and the respective theoretical considerations and justifications before finalizing our numerical experiments we hope to jump-start the incorporation of prototype-based learning in neural networks and vice versa.