Gossip-bAseD sub-GradiEnT SVM (GADGET SVM)
In the era of big data, an important weapon in a machine learning researcher’s arsenal is a scalable Support Vector Machine (SVM) algorithm. SVMs are extensively used for solving classification problems. Traditional algorithms for learning SVMs often scale super linearly with training set size which becomes infeasible very quickly for large data sets. In recent years, scalable algorithms have been designed which study the primal or dual formulations of the problem. This often suggests a way to decompose the problem and facilitate development of distributed algorithms. In this paper, we present a distributed algorithm for learning linear Support Vector Machines in the primal form for binary classification called Gossip-bAseD sub-GradiEnT (GADGET) SVM. The algorithm is designed such that it can be executed locally on nodes of a distributed system. Each node processes its local homogeneously partitioned data and learns a primal SVM model. It then gossips with random neighbors about the classifier learnt and uses this information to update the model. Extensive theoretical and empirical results suggest that this anytime algorithm has performance comparable to its centralized and online counterparts. …

Multi Preference Closure (MP-closure)
The paper describes a preferential approach for dealing with exceptions in KLM preferential logics, based on the rational closure. It is well known that the rational closure does not allow an independent handling of the inheritance of different defeasible properties of concepts. Several solutions have been proposed to face this problem and the lexicographic closure is the most notable one. In this work, we consider an alternative closure construction, called the Multi Preference closure (MP-closure), that has been first considered for reasoning with exceptions in DLs. Here, we reconstruct the notion of MP-closure in the propositional case and we show that it is a natural variant of Lehmann’s lexicographic closure. Abandoning Maximal Entropy (an alternative route already considered but not explored by Lehmann) leads to a construction which exploits a different lexicographic ordering w.r.t. the lexicographic closure, and determines a preferential consequence relation rather than a rational consequence relation. We show that, building on the MP-closure semantics, rationality can be recovered, at least from the semantic point of view, resulting in a rational consequence relation which is stronger than the rational closure, but incomparable with the lexicographic closure. We also show that the MP-closure is stronger than the Relevant Closure. …

Episodic Memory Reader (EMR)
We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently. …

BinGAN
In this paper, we propose a novel regularization method for Generative Adversarial Networks, which allows the model to learn discriminative yet compact binary representations of image patches (image descriptors). We employ the dimensionality reduction that takes place in the intermediate layers of the discriminator network and train binarized low-dimensional representation of the penultimate layer to mimic the distribution of the higher-dimensional preceding layers. To achieve this, we introduce two loss terms that aim at: (i) reducing the correlation between the dimensions of the binarized low-dimensional representation of the penultimate layer i. e. maximizing joint entropy) and (ii) propagating the relations between the dimensions in the high-dimensional space to the low-dimensional space. We evaluate the resulting binary image descriptors on two challenging applications, image matching and retrieval, and achieve state-of-the-art results. …

BabelNet
BabelNet is a multilingual lexicalized semantic network and ontology developed at the Linguistic Computing Laboratory in the Department of Computer Science of the Sapienza University of Rome. BabelNet was automatically created by linking the largest multilingual Web encyclopedia, Wikipedia, to the most popular computational lexicon of the English language, WordNet. The integration is performed by means of an automatic mapping and by filling in lexical gaps in resource-poor languages with the aid of statistical machine translation. The result is an ‘encyclopedic dictionary’ that provides concepts and named entities lexicalized in many languages and connected with large amounts of semantic relations. Additional lexicalizations and definitions are added by linking to free-license wordnets, OmegaWiki, the English Wiktionary and Wikidata. Similarly to WordNet, BabelNet groups words in different languages into sets of synonyms, called Babel synsets. For each Babel synset, BabelNet provides short definitions (called glosses) in many languages harvested from both WordNet and Wikipedia.
BabelNet …

AnchorNet
Despite significant progress of deep learning in recent years, state-of-the-art semantic matching methods still rely on legacy features such as SIFT or HoG. We argue that the strong invariance properties that are key to the success of recent deep architectures on the classification task make them unfit for dense correspondence tasks, unless a large amount of supervision is used. In this work, we propose a deep network, termed AnchorNet, that produces image representations that are well-suited for semantic matching. It relies on a set of filters whose response is geometrically consistent across different object instances, even in the presence of strong intra-class, scale, or viewpoint variations. Trained only with weak image-level labels, the final representation successfully captures information about the object structure and improves results of state-of-the-art semantic matching methods such as the deformable spatial pyramid or the proposal flow methods. We show positive results on the cross-instance matching task where different instances of the same object category are matched as well as on a new cross-category semantic matching task aligning pairs of instances each from a different object class. …

Computer Science
Computer science is the scientific and practical approach to computation and its applications. It is the systematic study of the feasibility, structure, expression, and mechanization of the methodical procedures (or algorithms) that underlie the acquisition, representation, processing, storage, communication of, and access to information, whether such information is encoded as bits in a computer memory or transcribed in genes and protein structures in a biological cell. An alternate, more succinct definition of computer science is the study of automating algorithmic processes that scale. A computer scientist specializes in the theory of computation and the design of computational systems. Its subfields can be divided into a variety of theoretical and practical disciplines. Some fields, such as computational complexity theory (which explores the fundamental properties of computational and intractable problems), are highly abstract, while fields such as computer graphics emphasize real-world visual applications. Still other fields focus on the challenges in implementing computation. For example, programming language theory considers various approaches to the description of computation, while the study of computer programming itself investigates various aspects of the use of programming language and complex systems. Human-computer interaction considers the challenges in making computers and computations useful, usable, and universally accessible to humans. …

Orthogonal Deep Neural Network (OrthDNN)
In this paper, we introduce the algorithms of Orthogonal Deep Neural Networks (OrthDNNs) to connect with recent interest of spectrally regularized deep learning methods. OrthDNNs are theoretically motivated by generalization analysis of modern DNNs, with the aim to find solution properties of network weights that guarantee better generalization. To this end, we first prove that DNNs are of local isometry on data distributions of practical interest; by using a new covering of the sample space and introducing the local isometry property of DNNs into generalization analysis, we establish a new generalization error bound that is both scale- and range-sensitive to singular value spectrum of each of networks’ weight matrices. We prove that the optimal bound w.r.t. the degree of isometry is attained when each weight matrix has a spectrum of equal singular values, among which orthogonal weight matrix or a non-square one with orthonormal rows or columns is the most straightforward choice, suggesting the algorithms of OrthDNNs. We present both algorithms of strict and approximate OrthDNNs, and for the later ones we propose a simple yet effective algorithm called Singular Value Bounding (SVB), which performs as well as strict OrthDNNs, but at a much lower computational cost. We also propose Bounded Batch Normalization (BBN) to make compatible use of batch normalization with OrthDNNs. We conduct extensive comparative studies by using modern architectures on benchmark image classification. Experiments show the efficacy of OrthDNNs. …

Persistent Identifier Kernel Information
Persistent Identifier (PID) is a widely used long-term unique reference to digital objects. Meanwhile, Handle, one of the main persistent identifier schemes in use, implements a central global registry to resolve PIDs. The value of Handle varies in sizes and types without any restrictions from user side. However, widely using the Handel raises challenges on managing and correlating different PIDs for users and curators. In this research paper, we raise an idea about the value of Handle, called Persistent Identifier Kernel Information, which is the critical metadata describing the minimal information for identifying the PID object. Simultaneously, an API service called Collection API, is collaborating with PID Kernel Information to manage the Backbone Provenance relationships among different PIDs. This paper is an early research exploration describing the strength and weakness of Collection API and PID Kernel Information. …

Modified Sequential Probability Ratio Test (MSPRT)
In a MSPRT design, the maximum sample size of an experiment is fixed prior to the start of an experiment, the alternative hypothesis used to define the rejection region of the test is derived from the size of the test (Type I error), the maximum available sample size (N), and the targeted Type 2 error (equal to 1 minus the power) is also prespecified. Given these values, the MSPRT is defined in a manner very similar to Wald’s initial proposal. This test can reduce the average sample size required to perform statistical hypothesis tests at the specified levels of significance and power. …

Tell Me Something New (TMSN)
We present a novel approach for parallel computation in the context of machine learning that we call ‘Tell Me Something New’ (TMSN). This approach involves a set of independent workers that use broadcast to update each other when they observe ‘something new’. TMSN does not require synchronization or a head node and is highly resilient against failing machines or laggards. We demonstrate the utility of TMSN by applying it to learning boosted trees. We show that our implementation is 10 times faster than XGBoost and LightGBM on the splice-site prediction problem. …

Hierarchical Temporal Convolutional Network (HierTCN)
Recommender systems that can learn from cross-session data to dynamically predict the next item a user will choose are crucial for online platforms. However, existing approaches often use out-of-the-box sequence models which are limited by speed and memory consumption, are often infeasible for production environments, and usually do not incorporate cross-session information, which is crucial for effective recommendations. Here we propose Hierarchical Temporal Convolutional Networks (HierTCN), a hierarchical deep learning architecture that makes dynamic recommendations based on users’ sequential multi-session interactions with items. HierTCN is designed for web-scale systems with billions of items and hundreds of millions of users. It consists of two levels of models: The high-level model uses Recurrent Neural Networks (RNN) to aggregate users’ evolving long-term interests across different sessions, while the low-level model is implemented with Temporal Convolutional Networks (TCN), utilizing both the long-term interests and the short-term interactions within sessions to predict the next interaction. We conduct extensive experiments on a public XING dataset and a large-scale Pinterest dataset that contains 6 million users with 1.6 billion interactions. We show that HierTCN is 2.5x faster than RNN-based models and uses 90% less data memory compared to TCN-based models. We further develop an effective data caching scheme and a queue-based mini-batch generator, enabling our model to be trained within 24 hours on a single GPU. Our model consistently outperforms state-of-the-art dynamic recommendation methods, with up to 18% improvement in recall and 10% in mean reciprocal rank. …

Probabilistic Binary Neural Network (BLRNet)
Low bit-width weights and activations are an effective way of combating the increasing need for both memory and compute power of Deep Neural Networks. In this work, we present a probabilistic training method for Neural Network with both binary weights and activations, called BLRNet. By embracing stochasticity during training, we circumvent the need to approximate the gradient of non-differentiable functions such as sign(), while still obtaining a fully Binary Neural Network at test time. Moreover, it allows for anytime ensemble predictions for improved performance and uncertainty estimates by sampling from the weight distribution. Since all operations in a layer of the BLRNet operate on random variables, we introduce stochastic versions of Batch Normalization and max pooling, which transfer well to a deterministic network at test time. We evaluate the BLRNet on multiple standardized benchmarks. …

Learning Solving Procedure
It is expected that progress toward true artificial intelligence will be achieved through the emergence of a system that integrates representation learning and complex reasoning (LeCun et al. 2015). In response to this prediction, research has been conducted on implementing the symbolic reasoning of a von Neumann computer in an artificial neural network (Graves et al. 2016; Graves et al. 2014; Reed et al. 2015). However, these studies have many limitations in realizing neural-symbolic integration (Jaeger. 2016). Here, we present a new learning paradigm: a learning solving procedure (LSP) that learns the procedure for solving complex problems. This is not accomplished merely by learning input-output data, but by learning algorithms through a solving procedure that obtains the output as a sequence of tasks for a given input problem. The LSP neural network system not only learns simple problems of addition and multiplication, but also the algorithms of complicated problems, such as complex arithmetic expression, sorting, and Hanoi Tower. To realize this, the LSP neural network structure consists of a deep neural network and long short-term memory, which are recursively combined. Through experimentation, we demonstrate the efficiency and scalability of LSP and its validity as a mechanism of complex reasoning. …

Probabilistic Computation Tree Logic (PCTL)
In this paper, we develop approximate dynamic programming methods for stochastic systems modeled as Markov Decision Processes, given both soft performance criteria and hard constraints in a class of probabilistic temporal logic called Probabilistic Computation Tree Logic (PCTL). Our approach consists of two steps: First, we show how to transform a class of PCTL formulas into chance constraints that can be enforced during planning in stochastic systems. Second, by integrating randomized optimization and entropy-regulated dynamic programming, we devise a novel trajectory sampling-based approximate value iteration method to iteratively solve for an upper bound on the value function while ensuring the constraints that PCTL specifications are satisfied. Particularly, we show that by the on-policy sampling of the trajectories, a tight bound can be achieved between the upper bound given by the approximation and the true value function. The correctness and efficiency of the method are demonstrated using robotic motion planning examples. …

Weight-Median Sketch
We introduce a new sub-linear space data structure—the Weight-Median Sketch—that captures the most heavily weighted features in linear classifiers trained over data streams. This enables memory-limited execution of several statistical analyses over streams, including online feature selection, streaming data explanation, relative deltoid detection, and streaming estimation of pointwise mutual information. In contrast with related sketches that capture the most commonly occurring features (or items) in a data stream, the Weight-Median Sketch captures the features that are most discriminative of one stream (or class) compared to another. The Weight-Median sketch adopts the core data structure used in the Count-Sketch, but, instead of sketching counts, it captures sketched gradient updates to the model parameters. We provide a theoretical analysis of this approach that establishes recovery guarantees in the online learning setting, and demonstrate substantial empirical improvements in accuracy-memory trade-offs over alternatives, including count-based sketches and feature hashing. …

cf2vec
Algorithm selection using Metalearning aims to find mappings between problem characteristics (i.e. metafeatures) with relative algorithm performance to predict the best algorithm(s) for new datasets. Therefore, it is of the utmost importance that the metafeatures used are informative. In Collaborative Filtering, recent research has created an extensive collection of such metafeatures. However, since these are created based on the practitioner’s understanding of the problem, they may not capture the most relevant aspects necessary to properly characterize the problem. We propose to overcome this problem by taking advantage of Representation Learning, which is able to create an alternative problem characterizations by having the data guide the design of the representation instead of the practitioner’s opinion. Our hypothesis states that such alternative representations can be used to replace standard metafeatures, hence hence leading to a more robust approach to Metalearning. We propose a novel procedure specially designed for Collaborative Filtering algorithm selection. The procedure models Collaborative Filtering as graphs and extracts distributed representations using graph2vec. Experimental results show that the proposed procedure creates representations that are competitive with state-of-the-art metafeatures, while requiring significantly less data and without virtually any human input. …

Dynamic Hierarchical Empirical Bayesian Model (DHEB)
Predicting keywords performance, such as number of impressions, click-through rate (CTR), conversion rate (CVR), revenue per click (RPC), and cost per click (CPC), is critical for sponsored search in the online advertising industry. An interesting phenomenon is that, despite the size of the overall data, the data are very sparse at the individual unit level. To overcome the sparsity and leverage hierarchical information across the data structure, we propose a Dynamic Hierarchical Empirical Bayesian (DHEB) model that dynamically determines the hierarchy through a data-driven process and provides shrinkage-based estimations. Our method is also equipped with an efficient empirical approach to derive inferences through the hierarchy. We evaluate the proposed method in both simulated and real-world datasets and compare to several competitive models. The results favor the proposed method among all comparisons in terms of both accuracy and efficiency. In the end, we design a two-phase system to serve prediction in real time. …

Generative Adversarial Self-Imitation Learning (GASIL)
This paper explores a simple regularizer for reinforcement learning by proposing Generative Adversarial Self-Imitation Learning (GASIL), which encourages the agent to imitate past good trajectories via generative adversarial imitation learning framework. Instead of directly maximizing rewards, GASIL focuses on reproducing past good trajectories, which can potentially make long-term credit assignment easier when rewards are sparse and delayed. GASIL can be easily combined with any policy gradient objective by using GASIL as a learned shaped reward function. Our experimental results show that GASIL improves the performance of proximal policy optimization on 2D Point Mass and MuJoCo environments with delayed reward and stochastic dynamics. …

Virtual Assistant Programming Language (VAPL)
To understand diverse natural language commands, virtual assistants today are trained with numerous labor-intensive, manually annotated sentences. This paper presents a methodology and the Genie toolkit that can handle new compound commands with significantly less manual effort. We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code. Genie needs only a small realistic set of input sentences for validating the neural model. Developers write templates to synthesize data; Genie uses crowdsourced paraphrases and data augmentation, along with the synthesized data, to train a semantic parser. We also propose design principles that make VAPL languages amenable to natural language translation. We apply these principles to revise ThingTalk, the language used by the Almond virtual assistant. We use Genie to build the first semantic parser that can support compound virtual assistants commands with unquoted free-form parameters. Genie achieves a 62% accuracy on realistic user inputs. We demonstrate Genie’s generality by showing a 19% and 31% improvement over the previous state of the art on a music skill, aggregate functions, and access control. …

Compositional GAN
Generative Adversarial Networks (GANs) can produce images of surprising complexity and realism, but are generally modeled to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could be present in a scene. Capturing such complex interactions between different objects in the world, including their relative scaling, spatial layout, occlusion, or viewpoint transformation is a challenging problem. In this work, we propose to model object composition in a GAN framework as a self-consistent composition-decomposition network. Our model is conditioned on the object images from their marginal distributions to generate a realistic image from their joint distribution by explicitly learning the possible interactions. We evaluate our model through qualitative experiments and user evaluations in both the scenarios when either paired or unpaired examples for the individual object images and the joint scenes are given during training. Our results reveal that the learned model captures potential interactions between the two object domains given as input to output new instances of composed scene at test time in a reasonable fashion. …

MIaS
Digital mathematical libraries (DMLs) such as arXiv, Numdam, and EuDML contain mainly documents from STEM fields, where mathematical formulae are often more important than text for understanding. Conventional information retrieval (IR) systems are unable to represent formulae and they are therefore ill-suited for math information retrieval (MIR). To fill the gap, we have developed, and open-sourced the MIaS MIR system. MIaS is based on the full-text search engine Apache Lucene. On top of text retrieval, MIaS also incorporates a set of tools for preprocessing mathematical formulae. We describe the design of the system and present speed, and quality evaluation results. We show that MIaS is both efficient, and effective, as evidenced by our victory in the NTCIR-11 Math-2 task. …

JointDNN
Deep neural networks are among the most influential architectures of deep learning algorithms, being deployed in many mobile intelligent applications. End-side services, such as intelligent personal assistants (IPAs), autonomous cars, and smart home services often employ either simple local models or complex remote models on the cloud. Mobile-only and cloud-only computations are currently the status quo approaches. In this paper, we propose an efficient, adaptive, and practical engine, JointDNN, for collaborative computation between a mobile device and cloud for DNNs in both inference and training phase. JointDNN not only provides an energy and performance efficient method of querying DNNs for the mobile side, but also benefits the cloud server by reducing the amount of its workload and communications compared to the cloud-only approach. Given the DNN architecture, we investigate the efficiency of processing some layers on the mobile device and some layers on the cloud server. We provide optimization formulations at layer granularity for forward and backward propagation in DNNs, which can adapt to mobile battery limitations and cloud server load constraints and quality of service. JointDNN achieves up to 18X and 32X reductions on the latency and mobile energy consumption of querying DNNs, respectively. …

In situ TensorView (TensorView)
Convolutional Neural Networks(CNNs) are complex systems. They are trained so they can adapt their internal connections to recognize images, texts and more. It is both interesting and helpful to visualize the dynamics within such deep artificial neural networks so that people can understand how these artificial networks are learning and making predictions. In the field of scientific simulations, visualization tools like Paraview have long been utilized to provide insights and understandings. We present in situ TensorView to visualize the training and functioning of CNNs as if they are systems of scientific simulations. In situ TensorView is a loosely coupled in situ visualization open framework that provides multiple viewers to help users to visualize and understand their networks. It leverages the capability of co-processing from Paraview to provide real-time visualization during training and predicting phases. This avoid heavy I/O overhead for visualizing large dynamic systems. Only a small number of lines of codes are injected in TensorFlow framework. The visualization can provide guidance to adjust the architecture of networks, or compress the pre-trained networks. We showcase visualizing the training of LeNet-5 and VGG16 using in situ TensorView. …

Embedding Transformation Network with Attention (ETNA)
Most companies utilize demographic information to develop their strategy in a market. However, such information is not available to most retail companies. Several studies have been conducted to predict the demographic attributes of users from their transaction histories, but they have some limitations. First, they focused on parameter sharing to predict all attributes but capturing task-specific features is also important in multi-task learning. Second, they assumed that all transactions are equally important in predicting demographic attributes. However, some transactions are more useful than others for predicting a certain attribute. Furthermore, decision making process of models cannot be interpreted as they work in a black-box manner. To address the limitations, we propose an Embedding Transformation Network with Attention (ETNA) model which shares representations at the bottom of the model structure and transforms them to task-specific representations using a simple linear transformation method. In addition, we can obtain more informative transactions for predicting certain attributes using the attention mechanism. The experimental results show that our model outperforms the previous models on all tasks. In our qualitative analysis, we show the visualization of attention weights, which provides business managers with some useful insights. …

Collaborative GAN Sampling
Generative adversarial networks (GANs) have shown great promise in generating complex data such as images. A standard practice in GANs is to discard the discriminator after training and use only the generator for sampling. However, this loses valuable information of real data distribution learned by the discriminator. In this work, we propose a collaborative sampling scheme between the generator and discriminator for improved data generation. Guided by the discriminator, our approach refines generated samples through gradient-based optimization, shifting the generator distribution closer to the real data distribution. Additionally, we present a practical discriminator shaping method that can further improve the sample refinement process. Orthogonal to existing GAN variants, our proposed method offers a new degree of freedom in GAN sampling. We demonstrate its efficacy through experiments on synthetic data and image generation tasks. …

Interactive Matching Network (IMN)
In this paper, we propose an interactive matching network (IMN) to enhance the representations of contexts and responses at both the word level and sentence level for the multi-turn response selection task. First, IMN constructs word representations from three aspects to address the challenge of out-of-vocabulary (OOV) words. Second, an attentive hierarchical recurrent encoder (AHRE), which is capable of encoding sentences hierarchically and generating more descriptive representations by aggregating with an attention mechanism, is designed. Finally, the bidirectional interactions between whole multi-turn contexts and response candidates are calculated to derive the matching information between them. Experiments on four public datasets show that IMN significantly outperforms the baseline models by large margins on all metrics, achieving new state-of-the-art performance and demonstrating compatibility across domains for multi-turn response selection. …

Boolean Satisfiability Problem (SAT)
In computer science, the Boolean satisfiability problem (sometimes called Propositional Satisfiability Problem and abbreviated as SATISFIABILITY or SAT) is the problem of determining if there exists an interpretation that satisfies a given Boolean formula. In other words, it asks whether the variables of a given Boolean formula can be consistently replaced by the values TRUE or FALSE in such a way that the formula evaluates to TRUE. If this is the case, the formula is called satisfiable. On the other hand, if no such assignment exists, the function expressed by the formula is FALSE for all possible variable assignments and the formula is unsatisfiable. For example, the formula ‘a AND NOT b’ is satisfiable because one can find the values a = TRUE and b = FALSE, which make (a AND NOT b) = TRUE. In contrast, ‘a AND NOT a’ is unsatisfiable. …

Chernoff Information
Chernoff information upper bounds the probability of error of the optimal Bayesian decision rule for 2 -class classification problems. However, it turns out that in practice the Chernoff bound is hard to calculate or even approximate. In statistics, many usual distributions, such as Gaussians, Poissons or frequency histograms called multinomials, can be handled in the unified framework of exponential families. In this note, we prove that the Chernoff information for members of the same exponential family can be either derived analytically in closed form, or efficiently approximated using a simple geodesic bisection optimization technique based on an exact geometric characterization of the ‘Chernoff point’ on the underlying statistical manifold. …

SCvx
This paper presents the SCvx algorithm, a successive convexification algorithm designed to solve non-convex optimal control problems with global convergence and superlinear convergence-rate guarantees. The proposed algorithm handles nonlinear dynamics and non-convex state and control constraints by linearizing them about the solution of the previous iterate, and solving the resulting convex subproblem to obtain a solution for the current iterate. Additionally, the algorithm incorporates several safe-guarding techniques into each convex subproblem, employing virtual controls and virtual buffer zones to avoid artificial infeasibility, and a trust region to avoid artificial unboundedness. The procedure is repeated in succession, thus turning a difficult non-convex optimal control problem into a sequence of numerically tractable convex subproblems. Using fast and reliable Interior Point Method (IPM) solvers, the convex subproblems can be computed quickly, making the SCvx algorithm well suited for real-time applications. Analysis is presented to show that the algorithm converges both globally and superlinearly, guaranteeing the local optimality of the original problem. The superlinear convergence is obtained by exploiting the structure of optimal control problems, showcasing the superior convergence rate that can be obtained by leveraging specific problem properties when compared to generic nonlinear programming methods. Numerical simulations are performed for an illustrative non-convex quad-rotor motion planning example problem, and corresponding results obtained using Sequential Quadratic Programming (SQP) solver are provided for comparison. Our results show that the convergence rate of the SCvx algorithm is indeed superlinear, and surpasses that of the SQP-based method by converging in less than half the number of iterations. …

MultiNet
Representation learning of networks via embeddings has garnered popularity and has witnessed significant progress recently. Such representations have been effectively used for classic network-based machine learning tasks like link prediction, community detection, and network alignment. However, most existing network embedding techniques largely focus on developing distributed representations for traditional flat networks and are unable to capture representations for multilayer networks. Large scale networks such as social networks and human brain tissue networks, for instance, can be effectively captured in multiple layers. In this work, we propose Multi-Net a fast and scalable embedding technique for multilayer networks. Our work adds a new wrinkle to the the recently introduced family of network embeddings like node2vec, LINE, DeepWalk, SIGNet, sub2vec, graph2vec, and OhmNet. We demonstrate the usability of Multi-Net by leveraging it to reconstruct the friends and followers network on Twitter using network layers mined from the body of tweets, like mentions network and the retweet network. This is the Work-in-progress paper and our preliminary contribution for multilayer network embeddings. …

Bayesian Allocation Model (BAM)
We introduce a dynamic generative model, Bayesian allocation model (BAM), which establishes explicit connections between nonnegative tensor factorization (NTF), graphical models of discrete probability distributions and their Bayesian extensions, and the topic models such as the latent Dirichlet allocation. BAM is based on a Poisson process, whose events are marked by using a Bayesian network, where the conditional probability tables of this network are then integrated out analytically. We show that the resulting marginal process turns out to be a Polya urn, an integer valued self-reinforcing process. This urn processes, which we name a Polya-Bayes process, obey certain conditional independence properties that provide further insight about the nature of NTF. These insights also let us develop space efficient simulation algorithms that respect the potential sparsity of data: we propose a class of sequential importance sampling algorithms for computing NTF and approximating their marginal likelihood, which would be useful for model selection. The resulting methods can also be viewed as a model scoring method for topic models and discrete Bayesian networks with hidden variables. The new algorithms have favourable properties in the sparse data regime when contrasted with variational algorithms that become more accurate when the total sum of the elements of the observed tensor goes to infinity. We illustrate the performance on several examples and numerically study the behaviour of the algorithms for various data regimes. …

Gradient Scheduling Algorithm With Global Momentum (GSGM)
Distributed asynchronous offline training has received widespread attention in recent years because of its high performance on large-scale data and complex models. As data are processed from cloud-centric positions to edge locations, a big challenge for distributed systems is how to handle native and natural non-independent and identically distributed (non-IID) data for training. Previous asynchronous training methods do not have a satisfying performance on non-IID data because it would result in that the training process fluctuates greatly which leads to an abnormal convergence. We propose a gradient scheduling algorithm with global momentum (GSGM) for non-IID data distributed asynchronous training. Our key idea is to schedule the gradients contributed by computing nodes based on a white list so that each training node’s update frequency remains even. Furthermore, our new momentum method can solve the biased gradient problem. GSGM can make model converge effectively, and maintain high availability eventually. Experimental results show that for non-IID data training under the same experimental conditions, GSGM on popular optimization algorithms can achieve an 20% increase in training stability with a slight improvement in accuracy on Fashion-Mnist and CIFAR-10 datasets. Meanwhile, when expanding distributed scale on CIFAR-100 dataset that results in sparse data distribution, GSGM can perform an 37% improvement on training stability. Moreover, only GSGM can converge well when the number of computing nodes is 30, compared to the state-of-the-art distributed asynchronous algorithms. …

Pena-Yohai Initial Estimator
Pena, D., & Yohai, V. (1999) <doi:10.2307/2670164>. …

Randomized Subspace Newton (RSN)
We develop a randomized Newton method capable of solving learning problems with huge dimensional feature spaces, which is a common setting in applications such as medical imaging, genomics and seismology. Our method leverages randomized sketching in a new way, by finding the Newton direction constrained to the space spanned by a random sketch. We develop a simple global linear convergence theory that holds for practically all sketching techniques, which gives the practitioners the freedom to design custom sketching approaches suitable for particular applications. We perform numerical experiments which demonstrate the efficiency of our method as compared to accelerated gradient descent and the full Newton method. Our method can be seen as a refinement and randomized extension of the results of Karimireddy, Stich, and Jaggi (2019). …

OCKELM+
Kernel method-based one-class classifier is mainly used for outlier or novelty detection. In this letter, kernel ridge regression (KRR) based one-class classifier (KOC) has been extended for learning using privileged information (LUPI). LUPI-based KOC method is referred to as KOC+. This privileged information is available as a feature with the dataset but only for training (not for testing). KOC+ utilizes the privileged information differently compared to normal feature information by using a so-called correction function. Privileged information helps KOC+ in achieving better generalization performance which is exhibited in this letter by testing the classifiers with and without privileged information. Existing and proposed classifiers are evaluated on the datasets from UCI machine learning repository and also on MNIST dataset. Moreover, experimental results evince the advantage of KOC+ over KOC and support vector machine (SVM) based one-class classifiers. …

Directed Random Geometric Graph (DRGG)
Many real-world networks are intrinsically directed. Such networks include activation of genes, hyperlinks on the internet, and the network of followers on Twitter among many others. The challenge, however, is to create a network model that has many of the properties of real-world networks such as powerlaw degree distributions and the small-world property. To meet these challenges, we introduce the \textit{Directed} Random Geometric Graph (DRGG) model, which is an extension of the random geometric graph model. We prove that it is scale-free with respect to the indegree distribution, has binomial outdegree distribution, has a high clustering coefficient, has few edges and is likely small-world. These are some of the main features of aforementioned real world networks. We empirically observe that word association networks have many of the theoretical properties of the DRGG model. …

Convolutional Neural Network with Bar Images (CNN-BI)
Even though computational intelligence techniques have been extensively utilized in financial trading systems, almost all developed models use the time series data for price prediction or identifying buy-sell points. However, in this study we decided to use 2-D stock bar chart images directly without introducing any additional time series associated with the underlying stock. We propose a novel algorithmic trading model CNN-BI (Convolutional Neural Network with Bar Images) using a 2-D Convolutional Neural Network. We generated 2-D images of sliding windows of 30-day bar charts for Dow 30 stocks and trained a deep Convolutional Neural Network (CNN) model for our algorithmic trading model. We tested our model separately between 2007-2012 and 2012-2017 for representing different market conditions. The results indicate that the model was able to outperform Buy and Hold strategy, especially in trendless or bear markets. Since this is a preliminary study and probably one of the first attempts using such an unconventional approach, there is always potential for improvement. Overall, the results are promising and the model might be integrated as part of an ensemble trading model combined with different strategies. …

Feedback Generative Adversarial Network (FBGAN)
Generative Adversarial Networks (GANs) represent an attractive and novel approach to generate realistic data, such as genes, proteins, or drugs, in synthetic biology. Here, we apply GANs to generate synthetic DNA sequences encoding for proteins of variable length. We propose a novel feedback-loop architecture, called Feedback GAN (FBGAN), to optimize the synthetic gene sequences for desired properties using an external function analyzer. The proposed architecture also has the advantage that the analyzer need not be differentiable. We apply the feedback-loop mechanism to two examples: 1) generating synthetic genes coding for antimicrobial peptides, and 2) optimizing synthetic genes for the secondary structure of their resulting peptides. A suite of metrics demonstrate that the GAN generated proteins have desirable biophysical properties. The FBGAN architecture can also be used to optimize GAN-generated datapoints for useful properties in domains beyond genomics. …

Subspace Clustering (SC)
Subspace clustering is a technique which finds clusters within different subspaces (a selection of one or more dimensions). The underlying assumption is that we can find valid clusters which are defined by only a subset of dimensions (it is not needed to have the agreement of all N features). For example, if we consider as input patient data observing the gene expression level (we can have more than 20000 features), a cluster of patients suffering from Alzheimer can be found only by looking at the expression data of a subset of 100 genes, or stated differently, the subset exists in 100D. Stated differently, subspace clustering is an extension of traditional N dimensional cluster analysis which allows to simultaneously group features and observations by creating both row and column clusters. The resulting clusters may be overlapping both in the space of features and observations. …