July 27, 2019

2876 words 14 mins read

Paper Group ANR 519

Growth-Optimal Portfolio Selection under CVaR Constraints. Morphological Error Detection in 3D Segmentations. Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits. ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases. Data-Driven Synthesis of Smoke Flows with CNN-based Feature …

Growth-Optimal Portfolio Selection under CVaR Constraints


Title	Growth-Optimal Portfolio Selection under CVaR Constraints
Authors	Guy Uziel, Ran El-Yaniv
Abstract	Online portfolio selection research has so far focused mainly on minimizing regret defined in terms of wealth growth. Practical financial decision making, however, is deeply concerned with both wealth and risk. We consider online learning of portfolios of stocks whose prices are governed by arbitrary (unknown) stationary and ergodic processes, where the goal is to maximize wealth while keeping the conditional value at risk (CVaR) below a desired threshold. We characterize the asymptomatically optimal risk-adjusted performance and present an investment strategy whose portfolios are guaranteed to achieve the asymptotic optimal solution while fulfilling the desired risk constraint. We also numerically demonstrate and validate the viability of our method on standard datasets.
Tasks	Decision Making
Published	2017-05-27
URL	http://arxiv.org/abs/1705.09800v1
PDF	http://arxiv.org/pdf/1705.09800v1.pdf
PWC	https://paperswithcode.com/paper/growth-optimal-portfolio-selection-under-cvar
Repo
Framework

Morphological Error Detection in 3D Segmentations


Title	Morphological Error Detection in 3D Segmentations
Authors	David Rolnick, Yaron Meirovitch, Toufiq Parag, Hanspeter Pfister, Viren Jain, Jeff W. Lichtman, Edward S. Boyden, Nir Shavit
Abstract	Deep learning algorithms for connectomics rely upon localized classification, rather than overall morphology. This leads to a high incidence of erroneously merged objects. Humans, by contrast, can easily detect such errors by acquiring intuition for the correct morphology of objects. Biological neurons have complicated and variable shapes, which are challenging to learn, and merge errors take a multitude of different forms. We present an algorithm, MergeNet, that shows 3D ConvNets can, in fact, detect merge errors from high-level neuronal morphology. MergeNet follows unsupervised training and operates across datasets. We demonstrate the performance of MergeNet both on a variety of connectomics data and on a dataset created from merged MNIST images.
Tasks
Published	2017-05-30
URL	http://arxiv.org/abs/1705.10882v1
PDF	http://arxiv.org/pdf/1705.10882v1.pdf
PWC	https://paperswithcode.com/paper/morphological-error-detection-in-3d
Repo
Framework

Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits


Title	Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits
Authors	Shahin Shahrampour, Vahid Tarokh
Abstract	We address the M-best-arm identification problem in multi-armed bandits. A player has a limited budget to explore K arms (M<K), and once pulled, each arm yields a reward drawn (independently) from a fixed, unknown distribution. The goal is to find the top M arms in the sense of expected reward. We develop an algorithm which proceeds in rounds to deactivate arms iteratively. At each round, the budget is divided by a nonlinear function of remaining arms, and the arms are pulled correspondingly. Based on a decision rule, the deactivated arm at each round may be accepted or rejected. The algorithm outputs the accepted arms that should ideally be the top M arms. We characterize the decay rate of the misidentification probability and establish that the nonlinear budget allocation proves to be useful for different problem environments (described by the number of competitive arms). We provide comprehensive numerical experiments showing that our algorithm outperforms the state-of-the-art using suitable nonlinearity.
Tasks	Multi-Armed Bandits
Published	2017-07-09
URL	http://arxiv.org/abs/1707.02649v1
PDF	http://arxiv.org/pdf/1707.02649v1.pdf
PWC	https://paperswithcode.com/paper/nonlinear-sequential-accepts-and-rejects-for
Repo
Framework

ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases


Title	ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
Authors	Pierre Stock, Moustapha Cisse
Abstract	ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of robustness of neural networks to adversarial examples and their tendency to exhibit undesirable biases question the reliability of these methods. This work investigates these questions from the perspective of the end-user by using human subject studies and explanations. The contribution of this study is threefold. We first experimentally demonstrate that the accuracy and robustness of ConvNets measured on Imagenet are vastly underestimated. Next, we show that explanations can mitigate the impact of misclassified adversarial examples from the perspective of the end-user. We finally introduce a novel tool for uncovering the undesirable biases learned by a model. These contributions also show that explanations are a valuable tool both for improving our understanding of ConvNets’ predictions and for designing more reliable models.
Tasks	Image Classification
Published	2017-11-30
URL	http://arxiv.org/abs/1711.11443v2
PDF	http://arxiv.org/pdf/1711.11443v2.pdf
PWC	https://paperswithcode.com/paper/convnets-and-imagenet-beyond-accuracy
Repo
Framework

Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors


Title	Data-Driven Synthesis of Smoke Flows with CNN-based Feature Descriptors
Authors	Mengyu Chu, Nils Thuerey
Abstract	We present a novel data-driven algorithm to synthesize high-resolution flow simulations with reusable repositories of space-time flow data. In our work, we employ a descriptor learning approach to encode the similarity between fluid regions with differences in resolution and numerical viscosity. We use convolutional neural networks to generate the descriptors from fluid data such as smoke density and flow velocity. At the same time, we present a deformation limiting patch advection method which allows us to robustly track deformable fluid regions. With the help of this patch advection, we generate stable space-time data sets from detailed fluids for our repositories. We can then use our learned descriptors to quickly localize a suitable data set when running a new simulation. This makes our approach very efficient, and resolution independent. We will demonstrate with several examples that our method yields volumes with very high effective resolutions, and non-dissipative small scale details that naturally integrate into the motions of the underlying flow.
Tasks
Published	2017-05-03
URL	http://arxiv.org/abs/1705.01425v2
PDF	http://arxiv.org/pdf/1705.01425v2.pdf
PWC	https://paperswithcode.com/paper/data-driven-synthesis-of-smoke-flows-with-cnn
Repo
Framework

Fast and Robust Detection of Fallen People from a Mobile Robot


Title	Fast and Robust Detection of Fallen People from a Mobile Robot
Authors	Morris Antonello, Marco Carraro, Marco Pierobon, Emanuele Menegatti
Abstract	This paper deals with the problem of detecting fallen people lying on the floor by means of a mobile robot equipped with a 3D depth sensor. In the proposed algorithm, inspired by semantic segmentation techniques, the 3D scene is over-segmented into small patches. Fallen people are then detected by means of two SVM classifiers: the first one labels each patch, while the second one captures the spatial relations between them. This novel approach showed to be robust and fast. Indeed, thanks to the use of small patches, fallen people in real cluttered scenes with objects side by side are correctly detected. Moreover, the algorithm can be executed on a mobile robot fitted with a standard laptop making it possible to exploit the 2D environmental map built by the robot and the multiple points of view obtained during the robot navigation. Additionally, this algorithm is robust to illumination changes since it does not rely on RGB data but on depth data. All the methods have been thoroughly validated on the IASLAB-RGBD Fallen Person Dataset, which is published online as a further contribution. It consists of several static and dynamic sequences with 15 different people and 2 different environments.
Tasks	Robot Navigation, Semantic Segmentation
Published	2017-03-09
URL	http://arxiv.org/abs/1703.03349v1
PDF	http://arxiv.org/pdf/1703.03349v1.pdf
PWC	https://paperswithcode.com/paper/fast-and-robust-detection-of-fallen-people
Repo
Framework

Towards automation of data quality system for CERN CMS experiment


Title	Towards automation of data quality system for CERN CMS experiment
Authors	Maxim Borisyak, Fedor Ratnikov, Denis Derkach, Andrey Ustyuzhanin
Abstract	Daily operation of a large-scale experiment is a challenging task, particularly from perspectives of routine monitoring of quality for data being taken. We describe an approach that uses Machine Learning for the automated system to monitor data quality, which is based on partial use of data qualified manually by detector experts. The system automatically classifies marginal cases: both of good an bad data, and use human expert decision to classify remaining “grey area” cases. This study uses collision data collected by the CMS experiment at LHC in 2010. We demonstrate that proposed workflow is able to automatically process at least 20% of samples without noticeable degradation of the result.
Tasks
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08607v1
PDF	http://arxiv.org/pdf/1709.08607v1.pdf
PWC	https://paperswithcode.com/paper/towards-automation-of-data-quality-system-for
Repo
Framework

Scalable Full Flow with Learned Binary Descriptors


Title	Scalable Full Flow with Learned Binary Descriptors
Authors	Gottfried Munda, Alexander Shekhovtsov, Patrick Knöbelreiter, Thomas Pock
Abstract	We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching. This enables evaluation of the cost on the fly and allows to perform learning and CRF inference on high resolution images without ever storing the 4D cost volume. To address the problem of learning binary descriptors we propose a new hybrid learning scheme. In contrast to current state of the art approaches for learning binary CNNs we can compute the exact non-zero gradient within our model. We compare several methods for training binary descriptors and show results on public available benchmarks.
Tasks	Optical Flow Estimation
Published	2017-07-20
URL	http://arxiv.org/abs/1707.06427v1
PDF	http://arxiv.org/pdf/1707.06427v1.pdf
PWC	https://paperswithcode.com/paper/scalable-full-flow-with-learned-binary
Repo
Framework

Threat analysis of IoT networks Using Artificial Neural Network Intrusion Detection System


Title	Threat analysis of IoT networks Using Artificial Neural Network Intrusion Detection System
Authors	Elike Hodo, Xavier Bellekens, Andrew Hamilton, Pierre-louis Dubouilh, Ephraim Iorkyase, Christos Tachtatzis, Robert Atkinson
Abstract	The Internet of things (IoT) is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using internet packet traces, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.
Tasks	Intrusion Detection, Network Intrusion Detection
Published	2017-04-07
URL	http://arxiv.org/abs/1704.02286v1
PDF	http://arxiv.org/pdf/1704.02286v1.pdf
PWC	https://paperswithcode.com/paper/threat-analysis-of-iot-networks-using
Repo
Framework

Collapsing of dimensionality


Title	Collapsing of dimensionality
Authors	Marco Gori, Marco Maggini, Alessandro Rossi
Abstract	We analyze a new approach to Machine Learning coming from a modification of classical regularization networks by casting the process in the time dimension, leading to a sort of collapse of dimensionality in the problem of learning the model parameters. This approach allows the definition of a online learning algorithm that progressively accumulates the knowledge provided in the input trajectory. The regularization principle leads to a solution based on a dynamical system that is paired with a procedure to develop a graph structure that stores the input regularities acquired from the temporal evolution. We report an extensive experimental exploration on the behavior of the parameter of the proposed model and an evaluation on artificial dataset.
Tasks
Published	2017-01-03
URL	http://arxiv.org/abs/1701.00831v1
PDF	http://arxiv.org/pdf/1701.00831v1.pdf
PWC	https://paperswithcode.com/paper/collapsing-of-dimensionality
Repo
Framework

Pixel Objectness


Title	Pixel Objectness
Authors	Suyog Dutt Jain, Bo Xiong, Kristen Grauman
Abstract	We propose an end-to-end learning framework for generating foreground object segmentations. Given a single novel image, our approach produces pixel-level masks for all “object-like” regions—even for object categories never seen during training. We formulate the task as a structured prediction problem of assigning foreground/background labels to all pixels, implemented using a deep fully convolutional network. Key to our idea is training with a mix of image-level object category examples together with relatively few images with boundary-level annotations. Our method substantially improves the state-of-the-art on foreground segmentation for ImageNet and MIT Object Discovery datasets. Furthermore, on over 1 million images, we show that it generalizes well to segment object categories unseen in the foreground maps used for training. Finally, we demonstrate how our approach benefits image retrieval and image retargeting, both of which flourish when given our high-quality foreground maps.
Tasks	Image Retrieval, Structured Prediction
Published	2017-01-19
URL	http://arxiv.org/abs/1701.05349v2
PDF	http://arxiv.org/pdf/1701.05349v2.pdf
PWC	https://paperswithcode.com/paper/pixel-objectness
Repo
Framework

Bit-Vector Model Counting using Statistical Estimation


Title	Bit-Vector Model Counting using Statistical Estimation
Authors	Seonmo Kim, Stephen McCamant
Abstract	Approximate model counting for bit-vector SMT formulas (generalizing #SAT) has many applications such as probabilistic inference and quantitative information-flow security, but it is computationally difficult. Adding random parity constraints (XOR streamlining) and then checking satisfiability is an effective approximation technique, but it requires a prior hypothesis about the model count to produce useful results. We propose an approach inspired by statistical estimation to continually refine a probabilistic estimate of the model count for a formula, so that each XOR-streamlined query yields as much information as possible. We implement this approach, with an approximate probability model, as a wrapper around an off-the-shelf SMT solver or SAT solver. Experimental results show that the implementation is faster than the most similar previous approaches which used simpler refinement strategies. The technique also lets us model count formulas over floating-point constraints, which we demonstrate with an application to a vulnerability in differential privacy mechanisms.
Tasks
Published	2017-12-21
URL	http://arxiv.org/abs/1712.07770v1
PDF	http://arxiv.org/pdf/1712.07770v1.pdf
PWC	https://paperswithcode.com/paper/bit-vector-model-counting-using-statistical
Repo
Framework

Understanding the Effective Receptive Field in Deep Convolutional Neural Networks


Title	Understanding the Effective Receptive Field in Deep Convolutional Neural Networks
Authors	Wenjie Luo, Yujia Li, Raquel Urtasun, Richard Zemel
Abstract	We study characteristics of receptive fields of units in deep convolutional networks. The receptive field size is a crucial issue in many visual tasks, as the output must respond to large enough areas in the image to capture information about large objects. We introduce the notion of an effective receptive field, and show that it both has a Gaussian distribution and only occupies a fraction of the full theoretical receptive field. We analyze the effective receptive field in several architecture designs, and the effect of nonlinear activations, dropout, sub-sampling and skip connections on it. This leads to suggestions for ways to address its tendency to be too small.
Tasks
Published	2017-01-15
URL	http://arxiv.org/abs/1701.04128v2
PDF	http://arxiv.org/pdf/1701.04128v2.pdf
PWC	https://paperswithcode.com/paper/understanding-the-effective-receptive-field
Repo
Framework

MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving


Title	MODNet: Moving Object Detection Network with Motion and Appearance for Autonomous Driving
Authors	Mennatullah Siam, Heba Mahgoub, Mohamed Zahran, Senthil Yogamani, Martin Jagersand, Ahmad El-Sallab
Abstract	We propose a novel multi-task learning system that combines appearance and motion cues for a better semantic reasoning of the environment. A unified architecture for joint vehicle detection and motion segmentation is introduced. In this architecture, a two-stream encoder is shared among both tasks. In order to evaluate our method in autonomous driving setting, KITTI annotated sequences with detection and odometry ground truth are used to automatically generate static/dynamic annotations on the vehicles. This dataset is called KITTI Moving Object Detection dataset (KITTI MOD). The dataset will be made publicly available to act as a benchmark for the motion detection task. Our experiments show that the proposed method outperforms state of the art methods that utilize motion cue only with 21.5% in mAP on KITTI MOD. Our method performs on par with the state of the art unsupervised methods on DAVIS benchmark for generic object segmentation. One of our interesting conclusions is that joint training of motion segmentation and vehicle detection benefits motion segmentation. Motion segmentation has relatively fewer data, unlike the detection task. However, the shared fusion encoder benefits from joint training to learn a generalized representation. The proposed method runs in 120 ms per frame, which beats the state of the art motion detection/segmentation in computational efficiency.
Tasks	Autonomous Driving, Motion Detection, Motion Segmentation, Multi-Task Learning, Object Detection, Semantic Segmentation
Published	2017-09-14
URL	http://arxiv.org/abs/1709.04821v2
PDF	http://arxiv.org/pdf/1709.04821v2.pdf
PWC	https://paperswithcode.com/paper/modnet-moving-object-detection-network-with
Repo
Framework

Identifying Quantum Phase Transitions with Adversarial Neural Networks


Title	Identifying Quantum Phase Transitions with Adversarial Neural Networks
Authors	Patrick Huembeli, Alexandre Dauphin, Peter Wittek
Abstract	The identification of phases of matter is a challenging task, especially in quantum mechanics, where the complexity of the ground state appears to grow exponentially with the size of the system. We address this problem with state-of-the-art deep learning techniques: adversarial domain adaptation. We derive the phase diagram of the whole parameter space starting from a fixed and known subspace using unsupervised learning. The input data set contains both labeled and unlabeled data instances. The first kind is a system that admits an accurate analytical or numerical solution, and one can recover its phase diagram. The second type is the physical system with an unknown phase diagram. Adversarial domain adaptation uses both types of data to create invariant feature extracting layers in a deep learning architecture. Once these layers are trained, we can attach an unsupervised learner to the network to find phase transitions. We show the success of this technique by applying it on several paradigmatic models: the Ising model with different temperatures, the Bose-Hubbard model, and the SSH model with disorder. The input is the ground state without any manual feature engineering, and the dimension of the parameter space is unrestricted. The method finds unknown transitions successfully and predicts transition points in close agreement with standard methods. This study opens the door to the classification of physical systems where the phases boundaries are complex such as the many-body localization problem or the Bose glass phase.
Tasks	Domain Adaptation, Feature Engineering
Published	2017-10-11
URL	http://arxiv.org/abs/1710.08382v2
PDF	http://arxiv.org/pdf/1710.08382v2.pdf
PWC	https://paperswithcode.com/paper/identifying-quantum-phase-transitions-with
Repo
Framework