October 20, 2019

3313 words 16 mins read

Paper Group ANR 20

Optimization of a SSP’s Header Bidding Strategy using Thompson Sampling. Backplay: “Man muss immer umkehren”. Smart Novel Computer-based Analytical Tool for Image Forgery Authentication. Synchronisation of Partial Multi-Matchings via Non-negative Factorisations. Matching Natural Language Sentences with Hierarchical Sentence Factorization. Unsupervi …

Optimization of a SSP’s Header Bidding Strategy using Thompson Sampling


Title	Optimization of a SSP’s Header Bidding Strategy using Thompson Sampling
Authors	Grégoire Jauvion, Nicolas Grislain, Pascal Sielenou Dkengne, Aurélien Garivier, Sébastien Gerchinovitz
Abstract	Over the last decade, digital media (web or app publishers) generalized the use of real time ad auctions to sell their ad spaces. Multiple auction platforms, also called Supply-Side Platforms (SSP), were created. Because of this multiplicity, publishers started to create competition between SSPs. In this setting, there are two successive auctions: a second price auction in each SSP and a secondary, first price auction, called header bidding auction, between SSPs.In this paper, we consider an SSP competing with other SSPs for ad spaces. The SSP acts as an intermediary between an advertiser wanting to buy ad spaces and a web publisher wanting to sell its ad spaces, and needs to define a bidding strategy to be able to deliver to the advertisers as many ads as possible while spending as little as possible. The revenue optimization of this SSP can be written as a contextual bandit problem, where the context consists of the information available about the ad opportunity, such as properties of the internet user or of the ad placement.Using classical multi-armed bandit strategies (such as the original versions of UCB and EXP3) is inefficient in this setting and yields a low convergence speed, as the arms are very correlated. In this paper we design and experiment a version of the Thompson Sampling algorithm that easily takes this correlation into account. We combine this bayesian algorithm with a particle filter, which permits to handle non-stationarity by sequentially estimating the distribution of the highest bid to beat in order to win an auction. We apply this methodology on two real auction datasets, and show that it significantly outperforms more classical approaches.The strategy defined in this paper is being developed to be deployed on thousands of publishers worldwide.
Tasks
Published	2018-07-09
URL	http://arxiv.org/abs/1807.03299v1
PDF	http://arxiv.org/pdf/1807.03299v1.pdf
PWC	https://paperswithcode.com/paper/optimization-of-a-ssps-header-bidding
Repo
Framework

Backplay: “Man muss immer umkehren”


Title	Backplay: “Man muss immer umkehren”
Authors	Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor, Alexander Peysakhovich, Kyunghyun Cho, Joan Bruna
Abstract	Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the sample efficiency when we have access to demonstrations. Our approach, Backplay, uses a single demonstration to construct a curriculum for a given task. Rather than starting each training episode in the environment’s fixed initial state, we start the agent near the end of the demonstration and move the starting point backwards during the course of training until we reach the initial state. Our contributions are that we analytically characterize the types of environments where Backplay can improve training speed, demonstrate the effectiveness of Backplay both in large grid worlds and a complex four player zero-sum game (Pommerman), and show that Backplay compares favorably to other competitive methods known to improve sample efficiency. This includes reward shaping, behavioral cloning, and reverse curriculum generation.
Tasks
Published	2018-07-18
URL	http://arxiv.org/abs/1807.06919v4
PDF	http://arxiv.org/pdf/1807.06919v4.pdf
PWC	https://paperswithcode.com/paper/backplay-man-muss-immer-umkehren
Repo
Framework

Smart Novel Computer-based Analytical Tool for Image Forgery Authentication


Title	Smart Novel Computer-based Analytical Tool for Image Forgery Authentication
Authors	Rozita Teymourzadeh, Amirrize Alpha, VH Mok
Abstract	This paper presents an integration of image forgery detection with image facial recognition using black propagation neural network (BPNN). We observed that facial image recognition by itself will always give a matching output or closest possible output image for every input image irrespective of the authenticity or otherwise not of the testing input image. Based on this, we are proposing the combination of the blind but powerful automation image forgery detection for entire input images for the BPNN recognition program. Hence, an input image must first be authenticated before being fed into the recognition program. Thus, an image security identification and authentication requirement, any image that fails the authentication/verification stage are not to be used as an input/test image. In addition, the universal smart GUI tool is proposed and designed to perform image forgery detection with the high accuracy of 2% error rate.
Tasks
Published	2018-06-10
URL	http://arxiv.org/abs/1806.04576v1
PDF	http://arxiv.org/pdf/1806.04576v1.pdf
PWC	https://paperswithcode.com/paper/smart-novel-computer-based-analytical-tool
Repo
Framework

Synchronisation of Partial Multi-Matchings via Non-negative Factorisations


Title	Synchronisation of Partial Multi-Matchings via Non-negative Factorisations
Authors	Florian Bernard, Johan Thunberg, Jorge Goncalves, Christian Theobalt
Abstract	In this work we study permutation synchronisation for the challenging case of partial permutations, which plays an important role for the problem of matching multiple objects (e.g. images or shapes). The term synchronisation refers to the property that the set of pairwise matchings is cycle-consistent, i.e. in the full matching case all compositions of pairwise matchings over cycles must be equal to the identity. Motivated by clustering and matrix factorisation perspectives of cycle-consistency, we derive an algorithm to tackle the permutation synchronisation problem based on non-negative factorisations. In order to deal with the inherent non-convexity of the permutation synchronisation problem, we use an initialisation procedure based on a novel rotation scheme applied to the solution of the spectral relaxation. Moreover, this rotation scheme facilitates a convenient Euclidean projection to obtain a binary solution after solving our relaxed problem. In contrast to state-of-the-art methods, our approach is guaranteed to produce cycle-consistent results. We experimentally demonstrate the efficacy of our method and show that it achieves better results compared to existing methods.
Tasks
Published	2018-03-16
URL	http://arxiv.org/abs/1803.06320v3
PDF	http://arxiv.org/pdf/1803.06320v3.pdf
PWC	https://paperswithcode.com/paper/synchronisation-of-partial-multi-matchings
Repo
Framework

Matching Natural Language Sentences with Hierarchical Sentence Factorization


Title	Matching Natural Language Sentences with Hierarchical Sentence Factorization
Authors	Bang Liu, Ting Zhang, Fred X. Han, Di Niu, Kunfeng Lai, Yu Xu
Abstract	Semantic matching of natural language sentences or identifying the relationship between two sentences is a core research problem underlying many natural language tasks. Depending on whether training data is available, prior research has proposed both unsupervised distance-based schemes and supervised deep learning schemes for sentence matching. However, previous approaches either omit or fail to fully utilize the ordered, hierarchical, and flexible structures of language objects, as well as the interactions between them. In this paper, we propose Hierarchical Sentence Factorization—a technique to factorize a sentence into a hierarchical representation, with the components at each different scale reordered into a “predicate-argument” form. The proposed sentence factorization technique leads to the invention of: 1) a new unsupervised distance metric which calculates the semantic distance between a pair of text snippets by solving a penalized optimal transport problem while preserving the logical relationship of words in the reordered sentences, and 2) new multi-scale deep learning models for supervised semantic training, based on factorized sentence hierarchies. We apply our techniques to text-pair similarity estimation and text-pair relationship classification tasks, based on multiple datasets such as STSbenchmark, the Microsoft Research paraphrase identification (MSRP) dataset, the SICK dataset, etc. Extensive experiments show that the proposed hierarchical sentence factorization can be used to significantly improve the performance of existing unsupervised distance-based metrics as well as multiple supervised deep learning models based on the convolutional neural network (CNN) and long short-term memory (LSTM).
Tasks	Paraphrase Identification
Published	2018-03-01
URL	http://arxiv.org/abs/1803.00179v1
PDF	http://arxiv.org/pdf/1803.00179v1.pdf
PWC	https://paperswithcode.com/paper/matching-natural-language-sentences-with
Repo
Framework

Unsupervised learning for concept detection in medical images: a comparative analysis


Title	Unsupervised learning for concept detection in medical images: a comparative analysis
Authors	Eduardo Pinho, Carlos Costa
Abstract	As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often scarce and short on annotations. In this paper, we present an assessment of unsupervised feature learning approaches for images in the biomedical literature, which can be applied to automatic biomedical concept detection. Six unsupervised representation learning methods were built, including traditional bags of visual words, autoencoders, and generative adversarial networks. Each model was trained, and their respective feature space evaluated using images from the ImageCLEF 2017 concept detection task. We conclude that it is possible to obtain more powerful representations with modern deep learning approaches, in contrast with previously popular computer vision methods. Although generative adversarial networks can provide good results, they are harder to succeed in highly varied data sets. The possibility of semi-supervised learning, as well as their use in medical information retrieval problems, are the next steps to be strongly considered.
Tasks	Information Retrieval, Representation Learning, Unsupervised Representation Learning
Published	2018-05-04
URL	http://arxiv.org/abs/1805.01803v1
PDF	http://arxiv.org/pdf/1805.01803v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-for-concept-detection
Repo
Framework

Face Recognition Using Map Discriminant on YCbCr Color Space


Title	Face Recognition Using Map Discriminant on YCbCr Color Space
Authors	I Gede Pasek Suta Wijaya
Abstract	This paper presents face recognition using maximum a posteriori (MAP) discriminant on YCbCr color space. The YCbCr color space is considered in order to cover the skin information of face image on the recognition process. The proposed method is employed to improve the recognition rate and equal error rate (EER) of the gray scale based face recognition. In this case, the face features vector consisting of small part of dominant frequency elements which is extracted by non-blocking DCT is implemented as dimensional reduction of the raw face images. The matching process between the query face features and the trained face features is performed using maximum a posteriori (MAP) discriminant. From the experimental results on data from four face databases containing 2268 images with 196 classes show that the face recognition YCbCr color space provide better recognition rate and lesser EER than those of gray scale based face recognition which improve the first rank of grayscale based method result by about 4%. However, it requires three times more computation time than that of grayscale based method.
Tasks	Face Recognition
Published	2018-07-05
URL	http://arxiv.org/abs/1807.02135v1
PDF	http://arxiv.org/pdf/1807.02135v1.pdf
PWC	https://paperswithcode.com/paper/face-recognition-using-map-discriminant-on
Repo
Framework

Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach


Title	Understanding Reuse, Performance, and Hardware Cost of DNN Dataflows: A Data-Centric Approach
Authors	Hyoukjun Kwon, Prasanth Chatarasi, Michael Pellauer, Angshuman Parashar, Vivek Sarkar, Tushar Krishna
Abstract	The data partitioning and scheduling strategies used by DNN accelerators to leverage reuse and perform staging are known as dataflow, and they directly impact the performance and energy efficiency of DNN accelerator designs. An accelerator microarchitecture dictates the dataflow(s) that can be employed to execute a layer or network. Selecting an optimal dataflow for a layer shape can have a large impact on utilization and energy efficiency, but there is a lack of understanding on the choices and consequences of dataflows, and of tools and methodologies to help architects explore the co-optimization design space. In this work, we first introduce a set of data-centric directives to concisely specify the space of DNN dataflows in a compilerfriendly form. We then show how these directives can be analyzed to infer various forms of reuse and to exploit them using hardware capabilities. We codify this analysis into an analytical cost model, MAESTRO (Modeling Accelerator Efficiency via Spatio-Temporal Reuse and Occupancy), that estimates various cost-benefit tradeoffs of a dataflow including execution time and energy efficiency for a DNN model and hardware configuration. We demonstrate the use of MAESTRO to drive a hardware design space exploration (DSE) experiment, which searches across 480M designs to identify 2.5M valid designs at an average rate of 0.17M designs per second, including Pareto-optimal throughput- and energy-optimized design points.
Tasks
Published	2018-05-04
URL	https://arxiv.org/abs/1805.02566v5
PDF	https://arxiv.org/pdf/1805.02566v5.pdf
PWC	https://paperswithcode.com/paper/a-data-centric-approach-for-modeling-and
Repo
Framework

Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing


Title	Low Precision Policy Distillation with Application to Low-Power, Real-time Sensation-Cognition-Action Loop with Neuromorphic Computing
Authors	Jeffrey L Mckinstry, Davis R. Barch, Deepika Bablani, Michael V. Debole, Steven K. Esser, Jeffrey A. Kusnitz, John V. Arthur, Dharmendra S. Modha
Abstract	Low precision networks in the reinforcement learning (RL) setting are relatively unexplored because of the limitations of binary activations for function approximation. Here, in the discrete action ATARI domain, we demonstrate, for the first time, that low precision policy distillation from a high precision network provides a principled, practical way to train an RL agent. As an application, on 10 different ATARI games, we demonstrate real-time end-to-end game playing on low-power neuromorphic hardware by converting a sequence of game frames into discrete actions.
Tasks	Atari Games
Published	2018-09-25
URL	http://arxiv.org/abs/1809.09260v1
PDF	http://arxiv.org/pdf/1809.09260v1.pdf
PWC	https://paperswithcode.com/paper/low-precision-policy-distillation-with
Repo
Framework

On Enhancing Genetic Algorithms Using New Crossovers


Title	On Enhancing Genetic Algorithms Using New Crossovers
Authors	Ahmad B. A. Hassanat, Esra’a Alkafaween
Abstract	This paper investigates the use of more than one crossover operator to enhance the performance of genetic algorithms. Novel crossover operators are proposed such as the Collision crossover, which is based on the physical rules of elastic collision, in addition to proposing two selection strategies for the crossover operators, one of which is based on selecting the best crossover operator and the other randomly selects any operator. Several experiments on some Travelling Salesman Problems (TSP) have been conducted to evaluate the proposed methods, which are compared to the well-known Modified crossover operator and partially mapped Crossover (PMX) crossover. The results show the importance of some of the proposed methods, such as the collision crossover, in addition to the significant enhancement of the genetic algorithms performance, particularly when using more than one crossover operator.
Tasks
Published	2018-01-08
URL	http://arxiv.org/abs/1801.02335v1
PDF	http://arxiv.org/pdf/1801.02335v1.pdf
PWC	https://paperswithcode.com/paper/on-enhancing-genetic-algorithms-using-new
Repo
Framework

A Study of Reinforcement Learning for Neural Machine Translation


Title	A Study of Reinforcement Learning for Neural Machine Translation
Authors	Lijun Wu, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu
Abstract	Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning. We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL training. Furthermore, to fill in the gap that it remains unclear whether RL is still beneficial when monolingual data is used, we propose a new method to leverage RL to further boost the performance of NMT systems trained with source/target monolingual data. By integrating all our findings, we obtain competitive results on WMT14 English- German, WMT17 English-Chinese, and WMT17 Chinese-English translation tasks, especially setting a state-of-the-art performance on WMT17 Chinese-English translation task.
Tasks	Machine Translation
Published	2018-08-27
URL	http://arxiv.org/abs/1808.08866v1
PDF	http://arxiv.org/pdf/1808.08866v1.pdf
PWC	https://paperswithcode.com/paper/a-study-of-reinforcement-learning-for-neural
Repo
Framework


Title	Vision-based Navigation of Autonomous Vehicle in Roadway Environments with Unexpected Hazards
Authors	Mhafuzul Islam, Mahsrur Chowdhury, Hongda Li, Hongxin Hu
Abstract	Vision-based navigation of autonomous vehicles primarily depends on the Deep Neural Network (DNN) based systems in which the controller obtains input from sensors/detectors, such as cameras and produces a vehicle control output, such as a steering wheel angle to navigate the vehicle safely in a roadway traffic environment. Typically, these DNN-based systems of the autonomous vehicle are trained through supervised learning; however, recent studies show that a trained DNN-based system can be compromised by perturbation or adversarial inputs. Similarly, this perturbation can be introduced into the DNN-based systems of autonomous vehicle by unexpected roadway hazards, such as debris and roadblocks. In this study, we first introduce a roadway hazardous environment (both intentional and unintentional roadway hazards) that can compromise the DNN-based navigational system of an autonomous vehicle, and produces an incorrect steering wheel angle, which can cause crashes resulting in fatality and injury. Then, we develop a DNN-based autonomous vehicle driving system using object detection and semantic segmentation to mitigate the adverse effect of this type of hazardous environment, which helps the autonomous vehicle to navigate safely around such hazards. We find that our developed DNN-based autonomous vehicle driving system including hazardous object detection and semantic segmentation improves the navigational ability of an autonomous vehicle to avoid a potential hazard by 21% compared to the traditional DNN-based autonomous vehicle driving system.
Tasks	Autonomous Driving, Autonomous Vehicles, Object Detection, Semantic Segmentation, Transfer Learning
Published	2018-09-27
URL	https://arxiv.org/abs/1810.03967v3
PDF	https://arxiv.org/pdf/1810.03967v3.pdf
PWC	https://paperswithcode.com/paper/vision-based-navigation-of-autonomous-vehicle
Repo
Framework

Spatial Uncertainty Sampling for End-to-End Control


Title	Spatial Uncertainty Sampling for End-to-End Control
Authors	Alexander Amini, Ava Soleimany, Sertac Karaman, Daniela Rus
Abstract	End-to-end trained neural networks (NNs) are a compelling approach to autonomous vehicle control because of their ability to learn complex tasks without manual engineering of rule-based decisions. However, challenging road conditions, ambiguous navigation situations, and safety considerations require reliable uncertainty estimation for the eventual adoption of full-scale autonomous vehicles. Bayesian deep learning approaches provide a way to estimate uncertainty by approximating the posterior distribution of weights given a set of training data. Dropout training in deep NNs approximates Bayesian inference in a deep Gaussian process and can thus be used to estimate model uncertainty. In this paper, we propose a Bayesian NN for end-to-end control that estimates uncertainty by exploiting feature map correlation during training. This approach achieves improved model fits, as well as tighter uncertainty estimates, than traditional element-wise dropout. We evaluate our algorithms on a challenging dataset collected over many different road types, times of day, and weather conditions, and demonstrate how uncertainties can be used in conjunction with a human controller in a parallel autonomous setting.
Tasks	Autonomous Vehicles, Bayesian Inference
Published	2018-05-13
URL	https://arxiv.org/abs/1805.04829v2
PDF	https://arxiv.org/pdf/1805.04829v2.pdf
PWC	https://paperswithcode.com/paper/spatial-uncertainty-sampling-for-end-to-end
Repo
Framework

Image Distortion Detection using Convolutional Neural Network


Title	Image Distortion Detection using Convolutional Neural Network
Authors	Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
Abstract	Image distortion classification and detection is an important task in many applications. For example when compressing images, if we know the exact location of the distortion, then it is possible to re-compress images by adjusting the local compression level dynamically. In this paper, we address the problem of detecting the distortion region and classifying the distortion type of a given image. We show that our model significantly outperforms the state-of-the-art distortion classifier, and report accurate detection results for the first time. We expect that such results prove the usefulness of our approach in many potential applications such as image compression or distortion restoration.
Tasks	Image Compression
Published	2018-05-28
URL	http://arxiv.org/abs/1805.10881v1
PDF	http://arxiv.org/pdf/1805.10881v1.pdf
PWC	https://paperswithcode.com/paper/image-distortion-detection-using
Repo
Framework

Confounder Detection in High Dimensional Linear Models using First Moments of Spectral Measures


Title	Confounder Detection in High Dimensional Linear Models using First Moments of Spectral Measures
Authors	Furui Liu, Laiwan Chan
Abstract	In this paper, we study the confounder detection problem in the linear model, where the target variable $Y$ is predicted using its $n$ potential causes $X_n=(x_1,…,x_n)^T$. Based on an assumption of rotation invariant generating process of the model, recent study shows that the spectral measure induced by the regression coefficient vector with respect to the covariance matrix of $X_n$ is close to a uniform measure in purely causal cases, but it differs from a uniform measure characteristically in the presence of a scalar confounder. Then, analyzing spectral measure pattern could help to detect confounding. In this paper, we propose to use the first moment of the spectral measure for confounder detection. We calculate the first moment of the regression vector induced spectral measure, and compare it with the first moment of a uniform spectral measure, both defined with respect to the covariance matrix of $X_n$. The two moments coincide in non-confounding cases, and differ from each other in the presence of confounding. This statistical causal-confounding asymmetry can be used for confounder detection. Without the need of analyzing the spectral measure pattern, our method does avoid the difficulty of metric choice and multiple parameter optimization. Experiments on synthetic and real data show the performance of this method.
Tasks
Published	2018-03-19
URL	http://arxiv.org/abs/1803.06852v2
PDF	http://arxiv.org/pdf/1803.06852v2.pdf
PWC	https://paperswithcode.com/paper/confounder-detection-in-high-dimensional
Repo
Framework