Multiple Hypotheses Propagation for Video Object Segmentation (MHP-VOS)
We address the problem of semi-supervised video object segmentation (VOS), where the masks of objects of interests are given in the first frame of an input video. To deal with challenging cases where objects are occluded or missing, previous work relies on greedy data association strategies that make decisions for each frame individually. In this paper, we propose a novel approach to defer the decision making for a target object in each frame, until a global view can be established with the entire video being taken into consideration. Our approach is in the same spirit as Multiple Hypotheses Tracking (MHT) methods, making several critical adaptations for the VOS problem. We employ the bounding box (bbox) hypothesis for tracking tree formation, and the multiple hypotheses are spawned by propagating the preceding bbox into the detected bbox proposals within a gated region starting from the initial object mask in the first frame. The gated region is determined by a gating scheme which takes into account a more comprehensive motion model rather than the simple Kalman filtering model in traditional MHT. To further design more customized algorithms tailored for VOS, we develop a novel mask propagation score instead of the appearance similarity score that could be brittle due to large deformations. The mask propagation score, together with the motion score, determines the affinity between the hypotheses during tree pruning. Finally, a novel mask merging strategy is employed to handle mask conflicts between objects. Extensive experiments on challenging datasets demonstrate the effectiveness of the proposed method, especially in the case of object missing. …

EvalNorm
Batch normalization (BN) has been very effective for deep learning and is widely used. However, when training with small minibatches, models using BN exhibit a significant degradation in performance. In this paper we study this peculiar behavior of BN to gain a better understanding of the problem, and identify a potential cause based on a statistical insight. We propose `EvalNorm’ to address the issue by estimating corrected normalization statistics to use for BN during evaluation. EvalNorm supports online estimation of the corrected statistics while the model is being trained, and it does not affect the training scheme of the model. As a result, an added advantage of EvalNorm is that it can be used with existing pre-trained models allowing them to benefit from our method. EvalNorm yields large gains for models trained with smaller batches. Our experiments show that EvalNorm performs 6.18% (absolute) better than vanilla BN for a batchsize of 2 on ImageNet validation set and from 1.5 to 7.0 points (absolute) gain on the COCO object detection benchmark across a variety of setups. …

Meaningful Purposive Interaction Analysis (MPIA)
This book introduces Meaningful Purposive Interaction Analysis (MPIA) theory, which combines social network analysis (SNA) with latent semantic analysis (LSA) to help create and analyse a meaningful learning landscape from the digital traces left by a learning community in the co-construction of knowledge. The hybrid algorithm is implemented in the statistical programming language and environment R, introducing packages which capture – through matrix algebra – elements of learners’ work with more knowledgeable others and resourceful content artefacts. The book provides comprehensive package-by-package application examples, and code samples that guide the reader through the MPIA model to show how the MPIA landscape can be constructed and the learner’s journey mapped and analysed. This building block application will allow the reader to progress to using and building analytics to guide students and support decision-making in learning. …

Superadditivity
In mathematics, a sequence { an }, n ≥ 1, is called superadditive if it satisfies the inequality a_{n+m} > a_n+a_m, for all m and n. The major reason for the use of superadditive sequences is the following lemma due to Michael Fekete. …

Vector of Locally-Aggregated Word Embedding (VLAWE)
In this paper, we propose a novel representation for text documents based on aggregating word embedding vectors into document embeddings. Our approach is inspired by the Vector of Locally-Aggregated Descriptors used for image representation, and it works as follows. First, the word embeddings gathered from a collection of documents are clustered by k-means in order to learn a codebook of semnatically-related word embeddings. Each word embedding is then associated to its nearest cluster centroid (codeword). The Vector of Locally-Aggregated Word Embeddings (VLAWE) representation of a document is then computed by accumulating the differences between each codeword vector and each word vector (from the document) associated to the respective codeword. We plug the VLAWE representation, which is learned in an unsupervised manner, into a classifier and show that it is useful for a diverse set of text classification tasks. We compare our approach with a broad range of recent state-of-the-art methods, demonstrating the effectiveness of our approach. Furthermore, we obtain a considerable improvement on the Movie Review data set, reporting an accuracy of 93.3%, which represents an absolute gain of 10% over the state-of-the-art approach. …

Non-AutOregressive Multiresolution Imputation (NAOMI)
Missing value imputation is a fundamental problem in modeling spatiotemporal sequences, from motion tracking to the dynamics of physical systems. In this paper, we take a non-autoregressive approach and propose a novel deep generative model: Non-AutOregressive Multiresolution Imputation (NAOMI) for imputing long-range spatiotemporal sequences given arbitrary missing patterns. In particular, NAOMI exploits the multiresolution structure of spatiotemporal data to interpolate recursively from coarse to fine-grained resolutions. We further enhance our model with adversarial training using an imitation learning objective. When trained on billiards and basketball trajectories, NAOMI demonstrates significant improvement in imputation accuracy (reducing average prediction error by 60% compared to autoregressive counterparts) and generalization capability for long range trajectories in systems of both deterministic and stochastic dynamics. …

Variational Information Bottleneck Approach (VIBI)
Briefness and comprehensiveness are necessary in order to give a lot of information concisely in explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, which may lead to redundant explanations. We propose a system-agnostic interpretable method that provides a brief but comprehensive explanation by adopting the inspiring information theoretic principle, information bottleneck principle. Using an information theoretic objective, VIBI selects instance-wise key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box on that input (comprehensive). The selected key features act as an information bottleneck that serves as a concise explanation for each black-box decision. We show that VIBI outperforms other interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics. …

Infinite Factorial Finite State Machine Model
New communication standards need to deal with machine-to-machine communications, in which users may start or stop transmitting at any time in an asynchronous manner. Thus, the number of users is an unknown and time-varying parameter that needs to be accurately estimated in order to properly recover the symbols transmitted by all users in the system. In this paper, we address the problem of joint channel parameter and data estimation in a multiuser communication channel in which the number of transmitters is not known. For that purpose, we develop the infinite factorial finite state machine model, a Bayesian nonparametric model based on the Markov Indian buffet that allows for an unbounded number of transmitters with arbitrary channel length. We propose an inference algorithm that makes use of slice sampling and particle Gibbs with ancestor sampling. Our approach is fully blind as it does not require a prior channel estimation step, prior knowledge of the number of transmitters, or any signaling information. Our experimental results, loosely based on the LTE random access channel, show that the proposed approach can effectively recover the data-generating process for a wide range of scenarios, with varying number of transmitters, number of receivers, constellation order, channel length, and signal-to-noise ratio. …

Collective Adaptive Resource-sharing Markovian Agents (CARMA)
In this paper we present CARMA, a language recently defined to support specification and analysis of collective adaptive systems. CARMA is a stochastic process algebra equipped with linguistic constructs specifically developed for modelling and programming systems that can operate in open-ended and unpredictable environments. This class of systems is typically composed of a huge number of interacting agents that dynamically adjust and combine their behaviour to achieve specific goals. A CARMA model, termed a collective, consists of a set of components, each of which exhibits a set of attributes. To model dynamic aggregations, which are sometimes referred to as ensembles, CARMA provides communication primitives that are based on predicates over the exhibited attributes. These predicates are used to select the participants in a communication. Two communication mechanisms are provided in the CARMA language: multicast-based and unicast-based. …

Bag-of-Concepts (BoC)
This paper focuses on a traditional relation extraction task in the context of limited annotated data and a narrow knowledge domain. We explore this task with a clinical corpus consisting of 200 breast cancer follow-up treatment letters in which 16 distinct types of relations are annotated. We experiment with an approach to extracting typed relations called window-bounded co-occurrence (WBC), which uses an adjustable context window around entity mentions of a relevant type, and compare its performance with a more typical intra-sentential co-occurrence baseline. We further introduce a new bag-of-concepts (BoC) approach to feature engineering based on the state-of-the-art word embeddings and word synonyms. We demonstrate the competitiveness of BoC by comparing with methods of higher complexity, and explore its effectiveness on this small dataset. …

Degree-Redundant-Influence (DRS)
Influence overlap is a universal phenomenon in influence spreading for social networks. In this paper, we argue that the redundant influence generated by influence overlap cause negative effect for maximizing spreading influence. Firstly, we present a theoretical method to calculate the influence overlap and record the redundant influence. Then in term of eliminating redundant influence, we present two algorithms, namely, Degree-Redundant-Influence (DRS) and Degree-Second-Neighborhood (DSN) for multiple spreaders identification. The experiments for four empirical social networks successfully verify the methods, and the spreaders selected by the DSN algorithm show smaller degree and k-core values. …

Multi-Round Distributed Linear-Type Estimator (MDL)
The growing size of modern data brings many new challenges to existing statistical inference methodologies and theories, and calls for the development of distributed inferential approaches. This paper studies distributed inference for linear support vector machine (SVM) for the binary classification task. Despite a vast literature on SVM, much less is known about the inferential properties of SVM, especially in a distributed setting. In this paper, we propose a multi-round distributed linear-type (MDL) estimator for conducting inference for linear SVM. The proposed estimator is computationally efficient. In particular, it only requires an initial SVM estimator and then successively refines the estimator by solving simple weighted least squares problem. Theoretically, we establish the Bahadur representation of the estimator. Based on the representation, the asymptotic normality is further derived, which shows that the MDL estimator achieves the optimal statistical efficiency, i.e., the same efficiency as the classical linear SVM applying to the entire dataset in a single machine setup. Moreover, our asymptotic result avoids the condition on the number of machines or data batches, which is commonly assumed in distributed estimation literature, and allows the case of diverging dimension. We provide simulation studies to demonstrate the performance of the proposed MDL estimator. …

MinoanER
Entity Resolution (ER) aims to identify different descriptions in various Knowledge Bases (KBs) that refer to the same entity. ER is challenged by the Variety, Volume and Veracity of entity descriptions published in the Web of Data. To address them, we propose the MinoanER framework that simultaneously fulfills full automation, support of highly heterogeneous entities, and massive parallelization of the ER process. MinoanER leverages a token-based similarity of entities to define a new metric that derives the similarity of neighboring entities from the most important relations, as they are indicated only by statistics. A composite blocking method is employed to capture different sources of matching evidence from the content, neighbors, or names of entities. The search space of candidate pairs for comparison is compactly abstracted by a novel disjunctive blocking graph and processed by a non-iterative, massively parallel matching algorithm that consists of four generic, schema-agnostic matching rules that are quite robust with respect to their internal configuration. We demonstrate that the effectiveness of MinoanER is comparable to existing ER tools over real KBs exhibiting low Variety, but it outperforms them significantly when matching KBs with high Variety. …

ParaGraphE
Knowledge graph embedding aims at translating the knowledge graph into numerical representations by transforming the entities and relations into con- tinuous low-dimensional vectors. Recently, many methods [1, 5, 3, 2, 6] have been proposed to deal with this problem, but existing single-thread implemen- tations of them are time-consuming for large-scale knowledge graphs. Here, we design a unified parallel framework to parallelize these methods, which achieves a significant time reduction without in uencing the accuracy. We name our framework as ParaGraphE, which provides a library for parallel knowledge graph embedding. The source code can be downloaded from https: //github.com/LIBBLE/LIBBLE-MultiThread/tree/master/ParaGraphE. …

Learned Step Size Quantization
We present here Learned Step Size Quantization, a method for training deep networks such that they can run at inference time using low precision integer matrix multipliers, which offer power and space advantages over high precision alternatives. The essence of our approach is to learn the step size parameter of a uniform quantizer by backpropagation of the training loss, applying a scaling factor to its learning rate, and computing its associated loss gradient by ignoring the discontinuity present in the quantizer. This quantization approach can be applied to activations or weights, using different levels of precision as needed for a given system, and requiring only a simple modification of existing training code. As demonstrated on the ImageNet dataset, our approach achieves better accuracy than all previous published methods for creating quantized networks on several ResNet network architectures at 2-, 3- and 4-bits of precision. …

FocusPixels
This paper describes AutoFocus, an efficient multi-scale inference algorithm for deep-learning based object detectors. Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales. This is achieved by predicting category agnostic segmentation maps for small objects at coarser scales, called FocusPixels. FocusPixels can be predicted with high recall, and in many cases, they only cover a small fraction of the entire image. To make efficient use of FocusPixels, an algorithm is proposed which generates compact rectangular FocusChips which enclose FocusPixels. The detector is only applied inside FocusChips, which reduces computation while processing finer scales. Different types of error can arise when detections from FocusChips of multiple scales are combined, hence techniques to correct them are proposed. AutoFocus obtains an mAP of 47.9% (68.3% at 50% overlap) on the COCO test-dev set while processing 6.4 images per second on a Titan X (Pascal) GPU. This is 2.5X faster than our multi-scale baseline detector and matches its mAP. The number of pixels processed in the pyramid can be reduced by 5X with a 1% drop in mAP. AutoFocus obtains more than 10% mAP gain compared to RetinaNet but runs at the same speed with the same ResNet-101 backbone. …

Dictionary Matching With k Mismatches
In the $k$-mismatch problem we are given a pattern of length $m$ and a text and must find all locations where the Hamming distance between the pattern and the text is at most $k$. A series of recent breakthroughs has resulted in an ultra-efficient streaming algorithm for this problem that requires only $O(k \log \frac{m}{k})$ space [Clifford, Kociumaka, Porat, 2017]. In this work we consider a strictly harder problem called dictionary matching with $k$ mismatches, where we are given a dictionary of $d$ patterns of lengths $\le m$ and must find all their $k$-mismatch occurrences in the text, and show the first streaming algorithm for it. The algorithm uses $O(k d \log^k d \; \mathrm{polylog} \; {m})$ space and processes each position of the text in $O(k \log^{k+1} d \; \mathrm{polylog} \; m + occ)$ time, where $occ$ is the number of $k$-mismatch occurrences of the patterns that end at this position. …

xtensor
Here we’re laying out a vision for the xtensor project, the n-dimensional array in the C++ language – that makes it easy to write high-performance code and bind it to the languages of data science (Python, Julia and R). …

DeepCABAC
We present DeepCABAC, a novel context-adaptive binary arithmetic coder for compressing deep neural networks. It quantizes each weight parameter by minimizing a weighted rate-distortion function, which implicitly takes the impact of quantization on to the accuracy of the network into account. Subsequently, it compresses the quantized values into a bitstream representation with minimal redundancies. We show that DeepCABAC is able to reach very high compression ratios across a wide set of different network architectures and datasets. For instance, we are able to compress by x63.6 the VGG16 ImageNet model with no loss of accuracy, thus being able to represent the entire network with merely 8.7MB. …

Re-forwarding
Deep Neutral Networks(DNN) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory is always finite, which limits the image resolution, batch size, and learning rate that could be tuned for better performances. In this paper, we propose a novel approach, called Re-forwarding, that substantially reduces memory usage in training. Our approach only saves the tensors at a subset of layers during the first forward, and conduct extra local forwards (the Re-forwarding process) to compute the missing tensors needed during backward. The total memory cost becomes the sum of (1) the cost at the subset of layers and (2) the maximum cost of the re-forwarding processes. We propose theories and algorithms that achieve the optimal memory solutions for DNNs with either linear or arbitrary optimization graphs. Experiments show that Re-forwarding cut down huge amount of training memory on all popular DNNs such as Alexnet, VGG net, ResNet, Densenet and Inception net. …

Maximum Percent Error (MPE)
To combine the proportions from different studies for meta-analysis, Freeman and Tukey double arcsine tranformation can be useful for normalization and variance stabilization. The inverse function of the double arcsine transformation has been also derived in the literature to recover the original scale of the proportion after aggregation. In this brief note, we present the domain and range of the inverse double arcsine transformation both analytically and graphically. We notice an erratic behavior in the mathematical formula for the inverse double arcsine tranformation at both limits of its domain, and propose approximation methods for both small and large samples. We also propose a simple accuracy measure, the maximum percent error (MPE), of the large sample approximation, which can be used to determine the sample size that would provide a certain accuracy level, and conversely to determine the accuracy level of the approximation given a sample size. …

Relational Proposal Graph Network (RepGN)
Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object detection from the graph learning perspective. Specifically, we present relational proposal graph network (RepGN) which is defined on object proposals and the semantic and spatial relation modeled as the edge. By integrating our RepGN module into object detectors, the relation and context constraints will be introduced to the feature extraction of regions and bounding boxes regression and classification. Besides, we propose a novel graph-cut based pooling layer for hierarchical coarsening of the graph, which empowers the RepGN module to exploit the inter-regional correlation and scene description in a hierarchical manner. We perform extensive experiments on COCO object detection dataset and show promising results. …

MC-ISTA-Net
The optimization inspired network can bridge convex optimization and neural networks in Compressive Sensing (CS) reconstruction of natural image, like ISTA-Net+, which mapping optimization algorithm: iterative shrinkage-thresholding algorithm (ISTA) into network. However, measurement matrix and input initialization are still hand-crafted, and multi-channel feature map contain information at different frequencies, which is treated equally across channels, hindering the ability of CS reconstruction in optimization-inspired networks. In order to solve the above problems, we proposed MC-ISTA-Net …

Stochastic Gradient Coding (SGC)
We consider distributed gradient descent in the presence of stragglers. Recent work on \em gradient coding \em and \em approximate gradient coding \em have shown how to add redundancy in distributed gradient descent to guarantee convergence even if some workers are \em stragglers\em—that is, slow or non-responsive. In this work we propose an approximate gradient coding scheme called \em Stochastic Gradient Coding \em (SGC), which works when the stragglers are random. SGC distributes data points redundantly to workers according to a pair-wise balanced design, and then simply ignores the stragglers. We prove that the convergence rate of SGC mirrors that of batched Stochastic Gradient Descent (SGD) for the $\ell_2$ loss function, and show how the convergence rate can improve with the redundancy. We also provide bounds for more general convex loss functions. We show empirically that SGC requires a small amount of redundancy to handle a large number of stragglers and that it can outperform existing approximate gradient codes when the number of stragglers is large. …

Kayenta
Kayenta is a platform for Automated Canary Analysis (ACA). It is used by Spinnaker to enable automated canary deployments. Please see the comprehensive canary documentation for more details. A canary release is a technique to reduce the risk from deploying a new version of software into production. A new version of software, referred to as the canary, is deployed to a small subset of users alongside the stable running version. Traffic is split between these two versions such that a portion of incoming requests are diverted to the canary. This approach can quickly uncover any problems with the new version without impacting the majority of users. The quality of the canary version is assessed by comparing key metrics that describe the behavior of the old and new versions. If there is significant degradation in these metrics, the canary is aborted and all of the traffic is routed to the stable version in an effort to minimize the impact of unexpected behavior. Canaries are usually run against deployments containing changes to code, but they can also be used for operational changes, including changes to configuration. …

Structured Parallel Programming Language for True Concurrency (SPPLTC)
Based on our previous work on algebraic laws for true concurrency, we design a skeleton of structured parallel programming language for true concurrency called SPPLTC. Different to most programming languages, SPPLTC has an explicit parallel operator as an essential operator. SPPLTC can structure a truly concurrent graph to a normal form. This means that it is possible to implement a compiler for SPPLTC. …

Multi-Objective Generalized Linear Bandits
In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied as online recommendation and network routing. On the other hand, these applications typically contain contextual information that can guide the learning process which, however, is ignored by most of existing work. To utilize this information, we associate each arm with a context vector and assume the reward follows the generalized linear model (GLM). We adopt the notion of Pareto regret to evaluate the learner’s performance and develop a novel algorithm for minimizing it. The essential idea is to apply a variant of the online Newton step to estimate model parameters, based on which we utilize the upper confidence bound (UCB) policy to construct an approximation of the Pareto front, and then uniformly at random choose one arm from the approximate Pareto front. Theoretical analysis shows that the proposed algorithm achieves an $\tilde O(d\sqrt{T})$ Pareto regret, where $T$ is the time horizon and $d$ is the dimension of contexts, which matches the optimal result for single objective contextual bandits problem. Numerical experiments demonstrate the effectiveness of our method. …

Delta-Screening
Community detection is a discovery tool used by network scientists to analyze the structure of real-world networks. It seeks to identify natural divisions that may exist in the input networks that partition the vertices into coherent modules (or communities). While this problem space is rich with efficient algorithms and software, most of this literature caters to the static use-case where the underlying network does not change. However, many emerging real-world use-cases give rise to a need to incorporate dynamic graphs as inputs. In this paper, we present a fast and efficient incremental approach toward dynamic community detection. The key contribution is a generic technique called $\Delta-screening$, which examines the most recent batch of changes made to an input graph and selects a subset of vertices to reevaluate for potential community (re)assignment. This technique can be incorporated into any of the community detection methods that use modularity as its objective function for clustering. For demonstration purposes, we incorporated the technique into two well-known community detection tools. Our experiments demonstrate that our new incremental approach is able to generate performance speedups without compromising on the output quality (despite its heuristic nature). For instance, on a real-world network with 63M temporal edges (over 12 time steps), our approach was able to complete in 1056 seconds, yielding a 3x speedup over a baseline implementation. In addition to demonstrating the performance benefits, we also show how to use our approach to delineate appropriate intervals of temporal resolutions at which to analyze an input network. …

Multiagent Soft Q-learning
Policy gradient methods are often applied to reinforcement learning in continuous multiagent games. These methods perform local search in the joint-action space, and as we show, they are susceptable to a game-theoretic pathology known as relative overgeneralization. To resolve this issue, we propose Multiagent Soft Q-learning, which can be seen as the analogue of applying Q-learning to continuous controls. We compare our method to MADDPG, a state-of-the-art approach, and show that our method achieves better coordination in multiagent cooperative tasks, converging to better local optima in the joint action space. …

Causal System
Jump to Search In Control Theory, a Causal System (also Known as a Physical or Nonanticipative System) is a System Where the Output Depends on Past and Current Inputs but not Future Inputs – I.e., the Output y ( t 0 ) {\displaystyle Y(t_{0})} Y(t_{{0}}) Depends on Only the Input x ( t ) {\displaystyle X(t)} X(t) for Values of t = t 0 {\displaystyle T\leq T_{0}} T\leq T_{{0}}. The Idea That the Output of a Function at any Time Depends Only on Past and Present Values of Input is Defined by the Property Commonly Referred to as Causality. A System That has Some Dependence on Input Values From the Future (in Addition to Possible Dependence on Past or Current Input Values) is Termed a non-Causal or Acausal System, and a System That Depends Solely on Future Input Values is an Anticausal System. Note That Some Authors Have Defined an Anticausal System as one That Depends Solely on Future and Present Input Values or, More Simply, as a System That Does not Depend on Past Input Values. Classically, Nature or Physical Reality has Been Considered to be a Causal System. Physics Involving Special Relativity or General Relativity Require More Careful Definitions of Causality, as Described Elaborately in Causality (physics). The Causality of Systems Also Plays an Important Role in Digital Signal Processing, Where Filters are Constructed so That They are Causal, Sometimes by Altering a non-Causal Formulation to Remove the Lack of Causality so That it is Realizable. For More Information, see Causal Filter. For a Causal System, the Impulse Response of the System Must use Only the Present and Past Values of the Input to Determine the Output. This Requirement is a Necessary and Sufficient Condition for a System to be Causal, Regardless of Linearity. Note That Similar Rules Apply to Either Discrete or Continuous Cases. By This Definition of Requiring no Future Input Values, Systems Must be Causal to Process Signals in Real Time.[1] …

Temperature Scaling (TS)
Confidence calibration – the problem of predicting probability estimates representative of the true correctness likelihood – is important for classification models in many applications. We discover that modern neural networks, unlike those from a decade ago, are poorly calibrated. Through extensive experiments, we observe that depth, width, weight decay, and Batch Normalization are important factors influencing calibration. We evaluate the performance of various post-processing calibration methods on state-ofthe- art architectures with image and document classification datasets. Our analysis and experiments not only offer insights into neural network learning, but also provide a simple and straightforward recipe for practical settings: on most datasets, temperature scaling – a singleparameter variant of Platt Scaling – is surprisingly effective at calibrating predictions. A New Loss Function for Temperature Scaling to have Better Calibrated Deep Networks …

DetNAS
Object detectors are usually equipped with networks designed for image classification as backbones, e.g., ResNet. Although it is publicly known that there is a gap between the task of image classification and object detection, designing a suitable detector backbone is still manually exhaustive. In this paper, we propose DetNAS to automatically search neural architectures for the backbones of object detectors. In DetNAS, the search space is formulated into a supernet and the search method relies on evolution algorithm (EA). In experiments, we show the effectiveness of DetNAS on various detectors, the one-stage detector, RetinaNet, and the two-stage detector, FPN. For each case, we search in both training from scratch scheme and ImageNet pre-training scheme. There is a consistent superiority compared to the architectures searched on ImageNet classification. Our main result architecture achieves better performance than ResNet-101 on COCO with the FPN detector. In addition, we illustrate the architectures searched by DetNAS and find some meaningful patterns. …

DAGOR
Effective overload control for large-scale online service system is crucial for protecting the system backend from overload. Conventionally, the design of overload control is ad-hoc for individual service. However, service-specific overload control could be detrimental to the overall system due to intricate service dependencies or flawed implementation of service. Service developers usually have difficulty to accurately estimate the dynamics of actual workload during the development of service. Therefore, it is essential to decouple the overload control from the service logic. In this paper, we propose DAGOR, an overload control scheme designed for the account-oriented microservice architecture. DAGOR is service agnostic and system-centric. It manages overload at the microservice granule such that each microservice monitors its load status in real time and triggers load shedding in a collaborative manner among its relevant services when overload is detected. DAGOR has been used in the WeChat backend for five years. Experimental results show that DAGOR can benefit high success rate of service even when the system is experiencing overload, while ensuring fairness in the overload control. …

Hierarchical Latent Dirichlet Allocation (H-LDA, HLDA)
An extension to LDA is the hierarchical LDA (hLDA), where topics are joined together in a hierarchy by using the nested Chinese restaurant process.
http://…/automatic-topic-modelling-with-lda …

GEMRank
Recently, word embedding algorithms have been applied to map the entities of recommender systems, such as users and items, to new feature spaces using textual element-context relations among them. Unlike many other domains, this approach has not achieved a desired performance in collaborative filtering problems, probably due to unavailability of appropriate textual data. In this paper we propose a new recommendation framework, called GEMRank that can be applied when the user-item matrix is the sole available souce of information. It uses the concept of profile co-occurrence for defining relations among entities and applies a factorization method for embedding the users and items. GEMRank then feeds the extracted representations to a neural network model to predict user-item like/dislike relations which the final recommendations are made based on. We evaluated GEMRank in an extensive set of experiments against state of the art recommendation methods. The results show that GEMRank significantly outperforms the baseline algorithms in a variety of data sets with different degrees of density. …

SMarTplan
Smart factories are on the verge of becoming the new industrial paradigm, wherein optimization permeates all aspects of production, from concept generation to sales. To fully pursue this paradigm, flexibility in the production means as well as in their timely organization is of paramount importance. AI is planning a major role in this transition, but the scenarios encountered in practice might be challenging for current tools. Task planning is one example where AI enables more efficient and flexible operation through an online automated adaptation and rescheduling of the activities to cope with new operational constraints and demands. In this paper we present SMarTplan, a task planner specifically conceived to deal with real-world scenarios in the emerging smart factory paradigm. Including both special-purpose and general-purpose algorithms, SMarTplan is based on current automated reasoning technology and it is designed to tackle complex application domains. In particular, we show its effectiveness on a logistic scenario, by comparing its specialized version with the general purpose one, and extending the comparison to other state-of-the-art task planners. …

Mixed-Integer Linear Programming (MILP)
This paper proposes an optimization strategy to assist utility operators to recover power distribution systems after large outages. Specifically, a novel mixed-integer linear programming (MILP) model is developed for co-optimizing crews, resources, and network operations. The MILP model coordinates the damage isolation, network reconfiguration, distributed generator re-dispatch, and crew/resource logistics. We consider two different types of crews, namely, line crews for damage repair and tree crews for obstacle removal. We also model the repair resource logistic constraints. Furthermore, a new algorithm is developed for solving the distribution system repair and restoration problem (DSRRP). The algorithm starts by solving DSRRP using an assignment-based method, then a neighborhood search method is designed to iteratively improve the solution. The proposed method is validated on the modified IEEE 123-bus distribution test system. …

Bayes via Goodness of fit
The two key issues of modern Bayesian statistics are: (i) establishing principled approach for distilling statistical prior that is consistent with the given data from an initial believable scientific prior; and (ii) development of a Bayes-frequentist consolidated data analysis workflow that is more effective than either of the two separately. In this paper, we propose the idea of ‘Bayes via goodness of fit’ as a framework for exploring these fundamental questions, in a way that is general enough to embrace almost all of the familiar probability models. Several illustrative examples show the benefit of this new point of view as a practical data analysis tool. Relationship with other Bayesian cultures is also discussed. …

Quantile Double Autoregression
Many financial time series have varying structures at different quantile levels, and also exhibit the phenomenon of conditional heteroscedasticity at the same time. In the meanwhile, it is still lack of a time series model to accommodate both of the above features simultaneously. This paper fills the gap by proposing a novel conditional heteroscedastic model, which is called the quantile double autoregression. The strict stationarity of the new model is derived, and a self-weighted conditional quantile estimation is suggested. Two promising properties of the original double autoregressive model are shown to be preserved. Based on the quantile autocorrelation function and self-weighting concept, two portmanteau tests are constructed, and they can be used in conjunction to check the adequacy of fitted conditional quantiles. The finite-sample performance of the proposed inference tools is examined by simulation studies, and the necessity of the new model is further demonstrated by analyzing the S&P500 Index. …

Destruction Rate
It is difficult to detect and remove secret images that are hidden in natural images using deep-learning algorithms. Our technique is the first work to effectively disable covert communications and transactions that use deep-learning steganography. We address the problem by exploiting sophisticated pixel distributions and edge areas of images using a deep neural network. Based on the given information, we adaptively remove secret information at the pixel level. We also introduce a new quantitative metric called destruction rate since the decoding method of deep-learning steganography is approximate (lossy), which is different from conventional steganography. We evaluate our technique using three public benchmarks in comparison with conventional steganalysis methods and show that the decoding rate improves by 10 ~ 20%. …