RankCGAN
In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical labels, our architecture handles both continuous and discrete scales. Given pairwise comparisons of images, our model, called RankCGAN, performs two tasks: it learns to rank images using a subjective measure; and it learns a generative model that can be controlled by that measure. RankCGAN associates each subjective measure of interest to a distinct dimension of some latent space. We perform experiments on UT-Zap50K, PubFig and OSR datasets and demonstrate that the model is expressive and diverse enough to conduct two-attribute exploration and image editing. …

Missing Value PC (MVPC)
Missing data are ubiquitous in many domains such as healthcare. Depending on how they are missing, the (conditional) independence relations in the observed data may be different from those for the complete data generated by the underlying causal process and, as a consequence, simply applying existing causal discovery methods to the observed data may lead to wrong conclusions. It is then essential to extend existing causal discovery approaches to find true underlying causal structure from such incomplete data. In this paper, we aim at solving this problem for data that are missing with different mechanisms, including missing completely at random (MCAR), missing at random (MAR), and missing not at random (MNAR). With missingness mechanisms represented by missingness Graph (m-Graph), we analyze conditions under which addition correction is needed to derive conditional independence/dependence relations in the complete data. Based on our analysis, we propose missing value PC (MVPC), which combines additional corrections with traditional causal discovery algorithm, in particular, PC. Our proposed MVPC is shown in theory to give asymptotically correct results even using data that are MAR and MNAR. Experiment results illustrate that the proposed algorithm can correct the conditional independence for values MCAR, MAR and rather general cases of values MNAR both with synthetic data as well as real-life healthcare application. …

Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization (DEEP-BO)
The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation. The code used is made publicly available at https://…/DEEP-BO. …

Three-Stage Subspace Clustering Framework (3S-SC)
Subspace clustering (SC) refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Based on spectral clustering, state-of-the-art approaches solve SC problem within a two-stage framework. In the first stage, data representation techniques are applied to draw an affinity matrix from the original data. In the second stage, spectral clustering is directly applied to the affinity matrix so that data can be grouped into different subspaces. However, the affinity matrix obtained in the first stage usually fails to reveal the authentic relationship between data points, which leads to inaccurate clustering results. In this paper, we propose a universal Three-Stage Subspace Clustering framework (3S-SC). Graph-Based Transformation and Optimization (GBTO) is added between data representation and spectral clustering. The affinity matrix is obtained in the first stage, then it goes through the second stage, where the proposed GBTO is applied to generate a reconstructed affinity matrix with more authentic similarity between data points. Spectral clustering is applied after GBTO, which is the third stage. We verify our 3S-SC framework with GBTO through theoretical analysis. Experiments on both synthetic data and the real-world data sets of handwritten digits and human faces demonstrate the universality of the proposed 3S-SC framework in improving the connectivity and accuracy of SC methods based on $\ell_0$, $\ell_1$, $\ell_2$ or nuclear norm regularization. …

Trainable Multiplication Layer
In this paper, we propose a trainable multiplication layer (TML) for a neural network that can be used to calculate the multiplication between the input features. Taking an image as an input, the TML raises each pixel value to the power of a weight and then multiplies them, thereby extracting the higher-order local auto-correlation from the input image. The TML can also be used to extract co-occurrence from the feature map of a convolutional network. The training of the TML is formulated based on backpropagation with constraints to the weights, enabling us to learn discriminative multiplication patterns in an end-to-end manner. In the experiments, the characteristics of the TML are investigated by visualizing learned kernels and the corresponding output features. The applicability of the TML for classification and neural network interpretation is also evaluated using public datasets. …

Total Operating Characteristic (TOC)
The relative operating characteristic (ROC) is a popular statistical method to measure the association between observed and diagnosed presence of a characteristic. The diagnosis of presence or absence depends on whether the value of an index variable is above a threshold. ROC considers multiple possible thresholds. Each threshold generates a two-by-two contingency table, which contains four central entries: hits, misses, false alarms, and correct rejections. ROC reveals for each threshold only two ratios, hits/(hits + misses) and false alarms/(false alarms + correct rejections). This article introduces the total operating characteristic (TOC), which shows the total information in the contingency table for each threshold. TOC maintains desirable properties of ROC, while TOC reveals strictly more information than ROC in a manner that makes TOC more useful than ROC. …

Lanczos Network (LanczosNet)
We propose the Lanczos network (LanczosNet), which uses the Lanczos algorithm to construct low rank approximations of the graph Laplacian for graph convolution. Relying on the tridiagonal decomposition of the Lanczos algorithm, we not only efficiently exploit multi-scale information via fast approximated computation of matrix power but also design learnable spectral filters. Being fully differentiable, LanczosNet facilitates both graph kernel learning as well as learning node embeddings. We show the connection between our LanczosNet and graph based manifold learning methods, especially the diffusion maps. We benchmark our model against several recent deep graph networks on citation networks and QM8 quantum chemistry dataset. Experimental results show that our model achieves the state-of-the-art performance in most tasks. …

CoachAI
Poor lifestyle represents a health risk factor and is the leading cause of morbidity and chronic conditions. The impact of poor lifestyle can be significantly altered by individual behavior change. Although the current shift in healthcare towards a long lasting modifiable behavior, however, with increasing caregiver workload and individuals’ continuous needs of care, there is a need to ease caregiver’s work while ensuring continuous interaction with users. This paper describes the design and validation of CoachAI, a conversational agent assisted health coaching system to support health intervention delivery to individuals and groups. CoachAI instantiates a text based healthcare chatbot system that bridges the remote human coach and the users. This research provides three main contributions to the preventive healthcare and healthy lifestyle promotion: (1) it presents the conversational agent to aid the caregiver; (2) it aims to decrease caregiver’s workload and enhance care given to users, by handling (automating) repetitive caregiver tasks; and (3) it presents a domain independent mobile health conversational agent for health intervention delivery. We will discuss our approach and analyze the results of a one month validation study on physical activity, healthy diet and stress management. …

Regularized Online Balanced Decent
We study online convex optimization in a setting where the learner seeks to minimize the sum of a per-round hitting cost and a movement cost which is incurred when changing decisions between rounds. We prove a new lower bound on the competitive ratio of any online algorithm in the setting where the costs are $m$-strongly convex and the movement costs are the squared $\ell_2$ norm. This lower bound shows that no algorithm can achieve a competitive ratio that is $o(m^{-1/2})$ as $m$ tends to zero. No existing algorithms have competitive ratios matching this bound, and we show that the state-of-the-art algorithm, Online Balanced Decent (OBD), has a competitive ratio that is $\Omega(m^{-2/3})$. We additionally propose two new algorithms, Greedy Online Balanced Decent (G-OBD) and Regularized Online Balanced Decent (R-OBD) and prove that both algorithms have an $O(m^{-1/2})$ competitive ratio. The result for G-OBD holds when the hitting costs are quasiconvex and the movement costs are the squared $\ell_2$ norm, while the result for R-OBD holds when the hitting costs are $m$-strongly convex and the movement costs are Bregman Divergences. Further, we show that R-OBD simultaneously achieves constant, dimension-free competitive ratio and sublinear regret when hitting costs are strongly convex. …

DeLTA
Training convolutional neural networks (CNNs) requires intense compute throughput and high memory bandwidth. Especially, convolution layers account for the majority of the execution time of CNN training, and GPUs are commonly used to accelerate these layer workloads. GPU design optimization for efficient CNN training acceleration requires the accurate modeling of how their performance improves when computing and memory resources are increased. We present DeLTA, the first analytical model that accurately estimates the traffic at each GPU memory hierarchy level, while accounting for the complex reuse patterns of a parallel convolution algorithm. We demonstrate that our model is both accurate and robust for different CNNs and GPU architectures. We then show how this model can be used to carefully balance the scaling of different GPU resources for efficient CNN performance improvement. …

Adaptive Collaborative Similarity Learning (ACSL)
In this paper, we investigate the research problem of unsupervised multi-view feature selection. Conventional solutions first simply combine multiple pre-constructed view-specific similarity structures into a collaborative similarity structure, and then perform the subsequent feature selection. These two processes are separate and independent. The collaborative similarity structure remains fixed during feature selection. Further, the simple undirected view combination may adversely reduce the reliability of the ultimate similarity structure for feature selection, as the view-specific similarity structures generally involve noises and outlying entries. To alleviate these problems, we propose an adaptive collaborative similarity learning (ACSL) for multi-view feature selection. We propose to dynamically learn the collaborative similarity structure, and further integrate it with the ultimate feature selection into a unified framework. Moreover, a reasonable rank constraint is devised to adaptively learn an ideal collaborative similarity structure with proper similarity combination weights and desirable neighbor assignment, both of which could positively facilitate the feature selection. An effective solution guaranteed with the proved convergence is derived to iteratively tackle the formulated optimization problem. Experiments demonstrate the superiority of the proposed approach. …

EXplicit interAction Model (EXAM)
Text classification is one of the fundamental tasks in natural language processing. Recently, deep neural networks have achieved promising performance in the text classification task compared to shallow models. Despite of the significance of deep models, they ignore the fine-grained (matching signals between words and classes) classification clues since their classifications mainly rely on the text-level representations. To address this problem, we introduce the interaction mechanism to incorporate word-level matching signals into the text classification task. In particular, we design a novel framework, EXplicit interAction Model (dubbed as EXAM), equipped with the interaction mechanism. We justified the proposed approach on several benchmark datasets including both multi-label and multi-class text classification tasks. Extensive experimental results demonstrate the superiority of the proposed method. As a byproduct, we have released the codes and parameter settings to facilitate other researches. …

Affective Computing
Affective computing (sometimes called artificial emotional intelligence, or emotion AI) is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. It is an interdisciplinary field spanning computer science, psychology, and cognitive science. While the origins of the field may be traced as far back as to early philosophical inquiries into emotion, the more modern branch of computer science originated with Rosalind Picard’s 1995 paper on affective computing. A motivation for the research is the ability to simulate empathy. The machine should interpret the emotional state of humans and adapt its behavior to them, giving an appropriate response to those emotions. The difference between sentiment analysis and affective analysis is that the latter detects the different emotions instead of identifying only the polarity of the phrase. …

VWPPR
Growing popularity of social networks demands a highly efficient Personalized PageRank (PPR) updating due to the fast-evolving web graphs of enormous size. While current researches are focusing on PPR updating under link structure modification, efficiently updating PPR when node insertion/ deletion involved remains a challenge. In the previous work called Virtual Web (VW), a few VW architectures are designed, which results in some highly effective initializations to significantly accelerate PageRank updating under both link modification and page insertion/deletion. In the paper, under the general scenario of link modification and node insertion/deletion we tackle the fast PPR updating problem. Specifically, we combine VW with the TrackingPPR method to generate initials, which are then used by the Gauss-Southwell method for fast PPR updating. The algorithm is named VWPPR method. In extensive experiments, three real-world datasets are used that contain 1~5.6M nodes and 6.7M~129M links, while a node perturbation of 40k and link perturbation of 1% are applied. Comparing to the more recent LazyForwardUpdate method, which handles the general PPR updating problem, the VWPPR method is 3~6 times faster in terms of running time, or 4.4~10 times faster in terms of iteration numbers. …

Fully Learnable Group Convolution Module (FLGC)
Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which is quite efficient and can be embedded into any deep neural networks for acceleration. Specifically, our proposed method automatically learns the group structure in the training stage in a fully end-to-end manner, leading to a better structure than the existing pre-defined, two-steps, or iterative strategies. Moreover, our method can be further combined with depthwise separable convolution, resulting in 5 times acceleration than the vanilla Resnet50 on single CPU. An additional advantage is that in our FLGC the number of groups can be set as any value, but not necessarily 2^k as in most existing methods, meaning better tradeoff between accuracy and speed. As evaluated in our experiments, our method achieves better performance than existing learnable group convolution and standard group convolution when using the same number of groups. …

DeepFlow
The calibration of a reservoir model with observed transient data of fluid pressures and rates is a key task in obtaining a predictive model of the flow and transport behaviour of the earth’s subsurface. The model calibration task, commonly referred to as ‘history matching’, can be formalised as an ill-posed inverse problem where we aim to find the underlying spatial distribution of petrophysical properties that explain the observed dynamic data. We use a generative adversarial network pretrained on geostatistical object-based models to represent the distribution of rock properties for a synthetic model of a hydrocarbon reservoir. The dynamic behaviour of the reservoir fluids is modelled using a transient two-phase incompressible Darcy formulation. We invert for the underlying reservoir properties by first modeling property distributions using the pre-trained generative model then using the adjoint equations of the forward problem to perform gradient descent on the latent variables that control the output of the generative model. In addition to the dynamic observation data, we include well rock-type constraints by introducing an additional objective function. Our contribution shows that for a synthetic test case, we are able to obtain solutions to the inverse problem by optimising in the latent variable space of a deep generative model, given a set of transient observations of a non-linear forward problem. …

JavaScript Object Notation (JSON)
JSON, or JavaScript Object Notation, is an open standard format that uses human-readable text to transmit data objects consisting of attribute-value pairs. It is used primarily to transmit data between a server and web application, as an alternative to XML. …

Causal Complementation Algorithm
The theory of linear Diophantine equations in two unknowns over polynomial rings is used to construct causal lifting factorizations for causal two-channel FIR perfect reconstruction multirate filter banks and wavelet transforms. The Diophantine approach generates causal lifting factorizations satisfying certain polynomial degree-reducing inequalities, enabling a new lifting factorization strategy called the \emph{Causal Complementation Algorithm}. This provides an alternative to the noncausal lifting scheme based on the Extended Euclidean Algorithm for Laurent polynomials that was developed by Daubechies and Sweldens. The new approach, which can be regarded as Gaussian elimination in polynomial matrices, utilizes a generalization of polynomial division that ensures existence and uniqueness of quotients whose remainders satisfy user-specified divisibility constraints. The Causal Complementation Algorithm is shown to be more general than the Extended Euclidean Algorithm approach by generating causal lifting factorizations not obtainable using the polynomial Euclidean Algorithm. …

Best-Scored Random Forest Classification
We propose an algorithm named best-scored random forest for binary classification problems. The terminology ‘best-scored’ means to select the one with the best empirical performance out of a certain number of purely random tree candidates as each single tree in the forest. In this way, the resulting forest can be more accurate than the original purely random forest. From the theoretical perspective, within the framework of regularized empirical risk minimization penalized on the number of splits, we establish almost optimal convergence rates for the proposed best-scored random trees under certain conditions which can be extended to the best-scored random forest. In addition, we present a counterexample to illustrate that in order to ensure the consistency of the forest, every dimension must have the chance to be split. In the numerical experiments, for the sake of efficiency, we employ an adaptive random splitting criterion. Comparative experiments with other state-of-art classification methods demonstrate the accuracy of our best-scored random forest. …

Berkeley Container Library (BCL)
One-sided communication is a useful paradigm for irregular parallel applications, but most one-sided programming environments, including MPI’s one-sided interface and PGAS programming languages, lack application level libraries to support these applications. We present the Berkeley Container Library, a set of generic, cross-platform, high-performance data structures for irregular applications, including queues, hash tables, Bloom filters and more. BCL is written in C++ using an internal DSL called the BCL Core that provides one-sided communication primitives such as remote get and remote put operations. The BCL Core has backends for MPI, OpenSHMEM, GASNet-EX, and UPC++, allowing BCL data structures to be used natively in programs written using any of these programming environments. Along with our internal DSL, we present the BCL ObjectContainer abstraction, which allows BCL data structures to transparently serialize complex data types while maintaining efficiency for primitive types. We also introduce the set of BCL data structures and evaluate their performance across a number of high-performance computing systems, demonstrating that BCL programs are competitive with hand-optimized code, even while hiding many of the underlying details of message aggregation, serialization, and synchronization. …

Uranie
The high-performance computing resources and the constant improvement of both numerical simulation accuracy and the experimental measurements with which they are confronted, bring a new compulsory step to strengthen the credence given to the simulation results: uncertainty quantification. This can have different meanings, according to the requested goals (rank uncertainty sources, reduce them, estimate precisely a critical threshold or an optimal working point) and it could request mathematical methods with greater or lesser complexity. This paper introduces the Uranie platform, an Open-source framework which is currently developed at the Alternative Energies and Atomic Energy Commission (CEA), in the nuclear energy division, in order to deal with uncertainty propagation, surrogate models, optimisation issues, code calibration… This platform benefits from both its dependencies, but also from personal developments, to offer an efficient data handling model, a C++ and Python interpreter, advanced graphical tools, several parallelisation solutions… These methods are very generic and can then be applied to many kinds of code (as Uranie considers them as black boxes) so to many fields of physics as well. In this paper, the example of thermal exchange between a plate-sheet and a fluid is introduced to show how Uranie can be used to perform a large range of analysis. The code used to produce the figures of this paper can be found in https://…/uranie along with the sources of the platform. …

Least Absolute Deviation (LAD)
Least absolute deviations (LAD), also known as least absolute errors (LAE), least absolute value (LAV), least absolute residual (LAR), sum of absolute deviations, or the L1 norm condition, is a statistical optimality criterion and the statistical optimization technique that relies on it. Similar to the popular least squares technique, it attempts to find a function which closely approximates a set of data. In the simple case of a set of (x,y) data, the approximation function is a simple ‘trend line’ in two-dimensional Cartesian coordinates. The method minimizes the sum of absolute errors (SAE) (the sum of the absolute values of the vertical ‘residuals’ between points generated by the function and corresponding points in the data). The least absolute deviations estimate also arises as the maximum likelihood estimate if the errors have a Laplace distribution. …

Hierarchical Data Format (HDF)
Hierarchical Data Format (HDF, HDF4, or HDF5) is a set of file formats and libraries designed to store and organize large amounts of numerical data. Originally developed at the National Center for Supercomputing Applications, it is supported by the non-profit HDF Group, whose mission is to ensure continued development of HDF5 technologies, and the continued accessibility of data stored in HDF. …

Infinite Latent Feature Selection
Feature selection is playing an increasingly significant role with respect to many computer vision applications spanning from object recognition to visual object tracking. However, most of the recent solutions in feature selection are not robust across different and heterogeneous set of data. In this paper, we address this issue proposing a robust probabilistic latent graph-based feature selection algorithm that performs the ranking step while considering all the possible subsets of features, as paths on a graph, bypassing the combinatorial problem analytically. An appealing characteristic of the approach is that it aims to discover an abstraction behind low-level sensory data, that is, relevancy. Relevancy is modelled as a latent variable in a PLSA-inspired generative process that allows the investigation of the importance of a feature when injected into an arbitrary set of cues. The proposed method has been tested on ten diverse benchmarks, and compared against eleven state of the art feature selection methods. Results show that the proposed approach attains the highest performance levels across many different scenarios and difficulties, thereby confirming its strong robustness while setting a new state of the art in feature selection domain. …

Generative Adversarial Network (GAN)
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake. This framework corresponds to a minimax two-player game. In the space of arbitrary functions G and D, a unique solution exists, with G recovering the training data distribution and D equal to 1/2 everywhere. In the case where G and D are defined by multilayer perceptrons, the entire system can be trained with backpropagation. There is no need for any Markov chains or unrolled approximate inference networks during either training or generation of samples. Experiments demonstrate the potential of the framework through qualitative and quantitative evaluation of the generated samples.
GitXiv …

BadNet
Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on many GPUs; as a result, many users outsource the training procedure to the cloud or rely on pre-trained models that are then fine-tuned for a specific task. In this paper we show that outsourced training introduces new security risks: an adversary can create a maliciously trained network (a backdoored neural network, or a \emph{BadNet}) that has state-of-the-art performance on the user’s training and validation samples, but behaves badly on specific attacker-chosen inputs. We first explore the properties of BadNets in a toy example, by creating a backdoored handwritten digit classifier. Next, we demonstrate backdoors in a more realistic scenario by creating a U.S. street sign classifier that identifies stop signs as speed limits when a special sticker is added to the stop sign; we then show in addition that the backdoor in our US street sign detector can persist even if the network is later retrained for another task and cause a drop in accuracy of {25}\% on average when the backdoor trigger is present. These results demonstrate that backdoors in neural networks are both powerful and—because the behavior of neural networks is difficult to explicate—stealthy. This work provides motivation for further research into techniques for verifying and inspecting neural networks, just as we have developed tools for verifying and debugging software. …

Stacked Dilated Convolution (SDC)
Dense pixel matching is important for many computer vision tasks such as disparity and flow estimation. We present a robust, unified descriptor network that considers a large context region with high spatial variance. Our network has a very large receptive field and avoids striding layers to maintain spatial resolution. These properties are achieved by creating a novel neural network layer that consists of multiple, parallel, stacked dilated convolutions (SDC). Several of these layers are combined to form our SDC descriptor network. In our experiments, we show that our SDC features outperform state-of-the-art feature descriptors in terms of accuracy and robustness. In addition, we demonstrate the superior performance of SDC in state-of-the-art stereo matching, optical flow and scene flow algorithms on several famous public benchmarks. …

Runtime Verification (RV)
Runtime verification is a computing system analysis and execution approach based on extracting information from a running system and using it to detect and possibly react to observed behaviors satisfying or violating certain properties. Some very particular properties, such as datarace and deadlock freedom, are typically desired to be satisfied by all systems and may be best implemented algorithmically. Other properties can be more conveniently captured as formal specifications. Runtime verification specifications are typically expressed in trace predicate formalisms, such as finite state machines, regular expressions, context-free patterns, linear temporal logics, etc., or extensions of these. This allows for a less ad-hoc approach than normal testing. However, any mechanism for monitoring an executing system is considered runtime verification, including verifying against test oracles and reference implementations. When formal requirements specifications are provided, monitors are synthesized from them and infused within the system by means of instrumentation. Runtime verification can be used for many purposes, such as security or safety policy monitoring, debugging, testing, verification, validation, profiling, fault protection, behavior modification (e.g., recovery), etc. Runtime verification avoids the complexity of traditional formal verification techniques, such as model checking and theorem proving, by analyzing only one or a few execution traces and by working directly with the actual system, thus scaling up relatively well and giving more confidence in the results of the analysis (because it avoids the tedious and error-prone step of formally modelling the system), at the expense of less coverage. Moreover, through its reflective capabilities runtime verification can be made an integral part of the target system, monitoring and guiding its execution during deployment. …

DeepCloud
Generative systems have a significant potential to synthesize innovative design alternatives. Still, most of the common systems that have been adopted in design require the designer to explicitly define the specifications of the procedures and in some cases the design space. In contrast, a generative system could potentially learn both aspects through processing a database of existing solutions without the supervision of the designer. To explore this possibility, we review recent advancements of generative models in machine learning and current applications of learning techniques in design. Then, we describe the development of a data-driven generative system titled DeepCloud. It combines an autoencoder architecture for point clouds with a web-based interface and analog input devices to provide an intuitive experience for data-driven generation of design alternatives. We delineate the implementation of two prototypes of DeepCloud, their contributions, and potentials for generative design. …

Structured Support Vector Machine
The structured support vector machine is a machine learning algorithm that generalizes the Support Vector Machine (SVM) classifier. Whereas the SVM classifier supports binary classification, multiclass classification and regression, the structured SVM allows training of a classifier for general structured output labels. As an example, a sample instance might be a natural language sentence, and the output label is an annotated parse tree. Training a classifier consists of showing pairs of correct sample and output label pairs. After training, the structured SVM model allows one to predict for new sample instances the corresponding output label; that is, given a natural language sentence, the classifier can produce the most likely parse tree.
➘ “Support Vector Machine” …

Semantic Adversarial Diagnostic Attack (SADA)
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their issues with robustness, which is essential for safety critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks for DNNs, which mostly focus on pixel-level perturbations void of semantic meaning. In contrast, we present a general framework for adversarial black box attacks on agents, which are intimately related to the semantics of the task being performed by the agent. To do this, our proposed adversary (denoted as BBGAN) is trained to appropriately parametrize the environment (black box) with which the agent interacts, such that this agent performs poorly on its dedicated task. We illustrate the application of our BBGAN framework on three different tasks (primarily targeting aspects of autonomous navigation): object detection, self-driving, and autonomous UAV racing. On these tasks, our approach can be used to generate failure cases that fool an agent consistently. …

Reverse Cuthill-McKee (RCM)
Ordering vertices of a graph is key to minimize fill-in and data structure size in sparse direct solvers, maximize locality in iterative solvers, and improve performance in graph algorithms. Except for naturally parallelizable ordering methods such as nested dissection, many important ordering methods have not been efficiently mapped to distributed-memory architectures. In this paper, we present the first-ever distributed-memory implementation of the reverse Cuthill-McKee (RCM) algorithm for reducing the profile of a sparse matrix. Our parallelization uses a two-dimensional sparse matrix decomposition. We achieve high performance by decomposing the problem into a small number of primitives and utilizing optimized implementations of these primitives. Our implementation shows strong scaling up to 1024 cores for smaller matrices and up to 4096 cores for larger matrices. …

Compatible Policy Search (COPOS)
Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a standard exponential policy distribution in combination with compatible value function approximation. Moreover, we show that standard natural gradient updates may reduce the entropy of the policy according to a wrong schedule leading to premature convergence. To control entropy reduction we introduce a new policy search method called compatible policy search (COPOS) which bounds entropy loss. The experimental results show that COPOS yields state-of-the-art results in challenging continuous control tasks and in discrete partially observable tasks. …

Stein’s Unbiased Risk Estimate (SURE)
Stein’s unbiased risk estimate (SURE) is an unbiased estimator of the mean-squared error of ‘a nearly arbitrary, nonlinear biased estimator.’ In other words, it provides an indication of the accuracy of a given estimator. This is important since the true mean-squared error of an estimator is a function of the unknown parameter to be estimated, and thus cannot be determined exactly. The technique is named after its discoverer, Charles Stein.
On an improvement of LASSO by scaling …

Textology
A Textology is a graph of word clusters connected by co-occurrence relations. …

Sliding Line Point Regression (SLPR)
Traditional text detection methods mostly focus on quadrangle text. In this study we propose a novel method named sliding line point regression (SLPR) in order to detect arbitrary-shape text in natural scene. SLPR regresses multiple points on the edge of text line and then utilizes these points to sketch the outlines of the text. The proposed SLPR can be adapted to many object detection architectures such as Faster R-CNN and R-FCN. Specifically, we first generate the smallest rectangular box including the text with region proposal network (RPN), then isometrically regress the points on the edge of text by using the vertically and horizontally sliding lines. To make full use of information and reduce redundancy, we calculate x-coordinate or y-coordinate of target point by the rectangular box position, and just regress the remaining y-coordinate or x-coordinate. Accordingly we can not only reduce the parameters of system, but also restrain the points which will generate more regular polygon. Our approach achieved competitive results on traditional ICDAR2015 Incidental Scene Text benchmark and curve text detection dataset CTW1500. …

Selective Forgetting
Few-shot learning is a challenging problem where the system is required to achieve generalization from only few examples. Meta-learning tackles the problem by learning prior knowledge shared across a distribution of tasks, which is then used to quickly adapt to unseen tasks. Model-agnostic meta-learning (MAML) algorithm formulates prior knowledge as a common initialization across tasks. However, forcibly sharing an initialization brings about conflicts between tasks and thus compromises the quality of the initialization. In this work, by observing that the extent of compromise differs among tasks and between layers of a neural network, we propose a new initialization idea that employs task-dependent layer-wise attenuation, which we call selective forgetting. The proposed attenuation scheme dynamically controls how much of prior knowledge each layer will exploit for a given task. The experimental results demonstrate that the proposed method mitigates the conflicts and provides outstanding performance as a result. We further show that the proposed method, named L2F, can be applied and improve other state-of-the-art MAML-based frameworks, illustrating its generalizability. …

Uncertainty-Aware Principal Component Analysis
We present a technique to perform dimensionality reduction on data that is subject to uncertainty. Our method is a generalization of traditional principal component analysis (PCA) to multivariate probability distributions. In comparison to non-linear methods, linear dimensionality reduction techniques have the advantage that the characteristics of such probability distributions remain intact after projection. We derive a representation of the covariance matrix that respects potential uncertainty in each of the observations, building the mathematical foundation of our new method uncertainty-aware PCA. In addition to the accuracy and performance gained by our approach over sampling-based strategies, our formulation allows us to perform sensitivity analysis with regard to the uncertainty in the data. For this, we propose factor traces as a novel visualization that enables us to better understand the influence of uncertainty on the chosen principal components. We provide multiple examples of our technique using real-world datasets and show how to propagate multivariate normal distributions through PCA in closed-form. Furthermore, we discuss extensions and limitations of our approach. …

Linear k-Junta
We study the problem of testing if a function depends on a small number of linear directions of its input data. We call a function $f$ a \emph{linear $k$-junta} if it is completely determined by some $k$-dimensional subspace of the input space. In this paper, we study the problem of testing whether a given $n$ variable function $f : \mathbb{R}^n \to $, is a linear $k$-junta or $\epsilon$-far from all linear $k$-juntas, where the closeness is measured with respect to the Gaussian measure on $\mathbb{R}^n$. This problems is a common generalization of (i) The combinatorial problem of junta testing on the hypercube which tests whether a Boolean function is dependent on at most $k$ of its variables and (ii) Geometric testing problems such as testing if a function is an intersection of $k$ halfspaces. We prove the existence of a $\mathsf{poly}(k \cdot s/\epsilon)$-query non-adaptive tester for linear $k$-juntas with surface area at most $s$. The polynomial dependence on $s$ is necessary as we provide a $\mathsf{poly}(s)$ lower bound on the query complexity of any non-adaptive test for linear juntas. Moreover, we show that if the function is a linear $k$-junta with surface area at most $s$, then there is a $(s \cdot k)^{O(k)}$-query non-adaptive algorithm to learn the function \emph{up to a rotation of the basis}. {We also use this procedure to obtain a non-adaptive tester (with the same query complexity) for subclasses of linear $k$-juntas closed under rotation.} …

Accelerated Alternating Projection
We study robust PCA for the fully observed setting, which is about separating a low rank matrix \BL \BL and a sparse matrix \BS \BS from their sum \BD=\BL+\BS \BD=\BL+\BS . In this paper, a new algorithm, dubbed accelerated alternating projections, is introduced for robust PCA which significantly improves the computational efficiency of the existing alternating projections proposed in (Netrapalli et al., 2014) when updating the low rank factor. The acceleration is achieved by first projecting a matrix onto some low dimensional subspace before obtaining a new estimate of the low rank matrix via truncated SVD. Exact recovery guarantee has been established which shows linear convergence of the proposed algorithm. Empirical performance evaluations establish the advantage of our algorithm over other state-of-the-art algorithms for robust PCA. …