October 17, 2019

2771 words 14 mins read

Paper Group ANR 848

Paper Group ANR 848

Large Scale Local Online Similarity/Distance Learning Framework based on Passive/Aggressive. AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning. Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting. Preventing Unnecessary Groundings in the Lifte …

Large Scale Local Online Similarity/Distance Learning Framework based on Passive/Aggressive

Title Large Scale Local Online Similarity/Distance Learning Framework based on Passive/Aggressive
Authors Baida Hamdan, Davood Zabihzadeh, Monsefi Reza
Abstract Similarity/Distance measures play a key role in many machine learning, pattern recognition, and data mining algorithms, which leads to the emergence of metric learning field. Many metric learning algorithms learn a global distance function from data that satisfy the constraints of the problem. However, in many real-world datasets that the discrimination power of features varies in the different regions of input space, a global metric is often unable to capture the complexity of the task. To address this challenge, local metric learning methods are proposed that learn multiple metrics across the different regions of input space. Some advantages of these methods are high flexibility and the ability to learn a nonlinear mapping but typically achieves at the expense of higher time requirement and overfitting problem. To overcome these challenges, this research presents an online multiple metric learning framework. Each metric in the proposed framework is composed of a global and a local component learned simultaneously. Adding a global component to a local metric efficiently reduce the problem of overfitting. The proposed framework is also scalable with both sample size and the dimension of input data. To the best of our knowledge, this is the first local online similarity/distance learning framework based on PA (Passive/Aggressive). In addition, for scalability with the dimension of input data, DRP (Dual Random Projection) is extended for local online learning in the present work. It enables our methods to be run efficiently on high-dimensional datasets, while maintains their predictive performance. The proposed framework provides a straightforward local extension to any global online similarity/distance learning algorithm based on PA.
Tasks Metric Learning
Published 2018-04-05
URL http://arxiv.org/abs/1804.01900v1
PDF http://arxiv.org/pdf/1804.01900v1.pdf
PWC https://paperswithcode.com/paper/large-scale-local-online-similaritydistance
Repo
Framework

AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning

Title AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
Authors Ahmed M. Alaa, Mihaela van der Schaar
Abstract Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTOPROGNOSIS: a system for automating the design of predictive modeling pipelines tailored for clinical prognosis. AUTOPROGNOSIS optimizes ensembles of pipeline configurations efficiently using a novel batched Bayesian optimization (BO) algorithm that learns a low-dimensional decomposition of the pipelines high-dimensional hyperparameter space in concurrence with the BO procedure. This is achieved by modeling the pipelines performances as a black-box function with a Gaussian process prior, and modeling the similarities between the pipelines baseline algorithms via a sparse additive kernel with a Dirichlet prior. Meta-learning is used to warmstart BO with external data from similar patient cohorts by calibrating the priors using an algorithm that mimics the empirical Bayes method. The system automatically explains its predictions by presenting the clinicians with logical association rules that link patients features to predicted risk strata. We demonstrate the utility of AUTOPROGNOSIS using 10 major patient cohorts representing various aspects of cardiovascular patient care.
Tasks Meta-Learning
Published 2018-02-20
URL http://arxiv.org/abs/1802.07207v1
PDF http://arxiv.org/pdf/1802.07207v1.pdf
PWC https://paperswithcode.com/paper/autoprognosis-automated-clinical-prognostic
Repo
Framework

Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting

Title Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Setting
Authors Artur Bekasov, Iain Murray
Abstract Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gilmer et al. (2018) introduced adversarial spheres, a toy set-up that simplifies both practical and theoretical analysis of the problem. In this work, we use the adversarial sphere set-up to understand the properties of approximate Bayesian inference methods for a linear model in a noiseless setting. We compare predictions of Bayesian and non-Bayesian methods, showcasing the advantages of the former, although revealing open challenges for deep learning applications.
Tasks Bayesian Inference
Published 2018-11-29
URL http://arxiv.org/abs/1811.12335v1
PDF http://arxiv.org/pdf/1811.12335v1.pdf
PWC https://paperswithcode.com/paper/bayesian-adversarial-spheres-bayesian
Repo
Framework

Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm

Title Preventing Unnecessary Groundings in the Lifted Dynamic Junction Tree Algorithm
Authors Marcel Gehrke, Tanya Braun, Ralf Möller
Abstract The lifted dynamic junction tree algorithm (LDJT) efficiently answers filtering and prediction queries for probabilistic relational temporal models by building and then reusing a first-order cluster representation of a knowledge base for multiple queries and time steps. Unfortunately, a non-ideal elimination order can lead to groundings even though a lifted run is possible for a model. We extend LDJT (i) to identify unnecessary groundings while proceeding in time and (ii) to prevent groundings by delaying eliminations through changes in a temporal first-order cluster representation. The extended version of LDJT answers multiple temporal queries orders of magnitude faster than the original version.
Tasks
Published 2018-07-02
URL http://arxiv.org/abs/1807.00744v1
PDF http://arxiv.org/pdf/1807.00744v1.pdf
PWC https://paperswithcode.com/paper/preventing-unnecessary-groundings-in-the
Repo
Framework

Delayed Impact of Fair Machine Learning

Title Delayed Impact of Fair Machine Learning
Authors Lydia T. Liu, Sarah Dean, Esther Rolf, Max Simchowitz, Moritz Hardt
Abstract Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventional wisdom suggests that fairness criteria promote the long-term well-being of those groups they aim to protect. We study how static fairness criteria interact with temporal indicators of well-being, such as long-term improvement, stagnation, and decline in a variable of interest. We demonstrate that even in a one-step feedback model, common fairness criteria in general do not promote improvement over time, and may in fact cause harm in cases where an unconstrained objective would not. We completely characterize the delayed impact of three standard criteria, contrasting the regimes in which these exhibit qualitatively different behavior. In addition, we find that a natural form of measurement error broadens the regime in which fairness criteria perform favorably. Our results highlight the importance of measurement and temporal modeling in the evaluation of fairness criteria, suggesting a range of new challenges and trade-offs.
Tasks
Published 2018-03-12
URL http://arxiv.org/abs/1803.04383v2
PDF http://arxiv.org/pdf/1803.04383v2.pdf
PWC https://paperswithcode.com/paper/delayed-impact-of-fair-machine-learning
Repo
Framework

Credit risk prediction in an imbalanced social lending environment

Title Credit risk prediction in an imbalanced social lending environment
Authors Anahita Namvar, Mohammad Siami, Fethi Rabhi, Mohsen Naderpour
Abstract Credit risk prediction is an effective way of evaluating whether a potential borrower will repay a loan, particularly in peer-to-peer lending where class imbalance problems are prevalent. However, few credit risk prediction models for social lending consider imbalanced data and, further, the best resampling technique to use with imbalanced data is still controversial. In an attempt to address these problems, this paper presents an empirical comparison of various combinations of classifiers and resampling techniques within a novel risk assessment methodology that incorporates imbalanced data. The credit predictions from each combination are evaluated with a G-mean measure to avoid bias towards the majority class, which has not been considered in similar studies. The results reveal that combining random forest and random under-sampling may be an effective strategy for calculating the credit risk associated with loan applicants in social lending markets.
Tasks
Published 2018-04-28
URL http://arxiv.org/abs/1805.00801v1
PDF http://arxiv.org/pdf/1805.00801v1.pdf
PWC https://paperswithcode.com/paper/credit-risk-prediction-in-an-imbalanced
Repo
Framework

Consistent sets of lines with no colorful incidence

Title Consistent sets of lines with no colorful incidence
Authors Boris Bukh, Xavier Goaoc, Alfredo Hubard, Matthew Trager
Abstract We consider incidences among colored sets of lines in $\mathbb{R}^d$ and examine whether the existence of certain concurrences between lines of $k$ colors force the existence of at least one concurrence between lines of $k+1$ colors. This question is relevant for problems in 3D reconstruction in computer vision.
Tasks 3D Reconstruction
Published 2018-03-16
URL http://arxiv.org/abs/1803.06267v1
PDF http://arxiv.org/pdf/1803.06267v1.pdf
PWC https://paperswithcode.com/paper/consistent-sets-of-lines-with-no-colorful
Repo
Framework

Attention-guided Unified Network for Panoptic Segmentation

Title Attention-guided Unified Network for Panoptic Segmentation
Authors Yanwei Li, Xinze Chen, Zheng Zhu, Lingxi Xie, Guan Huang, Dalong Du, Xingang Wang
Abstract This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level. Existing methods mostly dealt with these two problems separately, but in this paper, we reveal the underlying relationship between them, in particular, FG objects provide complementary cues to assist BG understanding. Our approach, named the Attention-guided Unified Network (AUNet), is a unified framework with two branches for FG and BG segmentation simultaneously. Two sources of attentions are added to the BG branch, namely, RPN and FG segmentation mask to provide object-level and pixel-level attentions, respectively. Our approach is generalized to different backbones with consistent accuracy gain in both FG and BG segmentation, and also sets new state-of-the-arts both in the MS-COCO (46.5% PQ) and Cityscapes (59.0% PQ) benchmarks.
Tasks Panoptic Segmentation
Published 2018-12-10
URL http://arxiv.org/abs/1812.03904v2
PDF http://arxiv.org/pdf/1812.03904v2.pdf
PWC https://paperswithcode.com/paper/attention-guided-unified-network-for-panoptic
Repo
Framework

Uniform Inference in High-Dimensional Gaussian Graphical Models

Title Uniform Inference in High-Dimensional Gaussian Graphical Models
Authors Sven Klaassen, Jannis Kück, Martin Spindler, Victor Chernozhukov
Abstract Graphical models have become a very popular tool for representing dependencies within a large set of variables and are key for representing causal structures. We provide results for uniform inference on high-dimensional graphical models with the number of target parameters $d$ being possible much larger than sample size. This is in particular important when certain features or structures of a causal model should be recovered. Our results highlight how in high-dimensional settings graphical models can be estimated and recovered with modern machine learning methods in complex data sets. To construct simultaneous confidence regions on many target parameters, sufficiently fast estimation rates of the nuisance functions are crucial. In this context, we establish uniform estimation rates and sparsity guarantees of the square-root estimator in a random design under approximate sparsity conditions that might be of independent interest for related problems in high-dimensions. We also demonstrate in a comprehensive simulation study that our procedure has good small sample properties.
Tasks
Published 2018-08-30
URL http://arxiv.org/abs/1808.10532v2
PDF http://arxiv.org/pdf/1808.10532v2.pdf
PWC https://paperswithcode.com/paper/uniform-inference-in-high-dimensional
Repo
Framework

Reinforcement Learning based QoS/QoE-aware Service Function Chaining in Software-Driven 5G Slices

Title Reinforcement Learning based QoS/QoE-aware Service Function Chaining in Software-Driven 5G Slices
Authors Xi Chen, Zonghang Li, Yupeng Zhang, Ruiming Long, Hongfang Yu, Xiaojiang Du, Mohsen Guizani
Abstract With the ever growing diversity of devices and applications that will be connected to 5G networks, flexible and agile service orchestration with acknowledged QoE that satisfies end-user’s functional and QoS requirements is necessary. SDN (Software-Defined Networking) and NFV (Network Function Virtualization) are considered key enabling technologies for 5G core networks. In this regard, this paper proposes a reinforcement learning based QoS/QoE-aware Service Function Chaining (SFC) in SDN/NFV-enabled 5G slices. First, it implements a lightweight QoS information collector based on LLDP, which works in a piggyback fashion on the southbound interface of the SDN controller, to enable QoS-awareness. Then, a DQN (Deep Q Network) based agent framework is designed to support SFC in the context of NFV. The agent takes into account the QoE and QoS as key aspects to formulate the reward so that it is expected to maximize QoE while respecting QoS constraints. The experiment results show that this framework exhibits good performance in QoE provisioning and QoS requirements maintenance for SFC in dynamic network environments.
Tasks
Published 2018-04-06
URL http://arxiv.org/abs/1804.02099v1
PDF http://arxiv.org/pdf/1804.02099v1.pdf
PWC https://paperswithcode.com/paper/reinforcement-learning-based-qosqoe-aware
Repo
Framework

Tight Regret Bounds for Bayesian Optimization in One Dimension

Title Tight Regret Bounds for Bayesian Optimization in One Dimension
Authors Jonathan Scarlett
Abstract We consider the problem of Bayesian optimization (BO) in one dimension, under a Gaussian process prior and Gaussian sampling noise. We provide a theoretical analysis showing that, under fairly mild technical assumptions on the kernel, the best possible cumulative regret up to time $T$ behaves as $\Omega(\sqrt{T})$ and $O(\sqrt{T\log T})$. This gives a tight characterization up to a $\sqrt{\log T}$ factor, and includes the first non-trivial lower bound for noisy BO. Our assumptions are satisfied, for example, by the squared exponential and Mat'ern-$\nu$ kernels, with the latter requiring $\nu > 2$. Our results certify the near-optimality of existing bounds (Srinivas {\em et al.}, 2009) for the SE kernel, while proving them to be strictly suboptimal for the Mat'ern kernel with $\nu > 2$.
Tasks
Published 2018-05-30
URL https://arxiv.org/abs/1805.11792v2
PDF https://arxiv.org/pdf/1805.11792v2.pdf
PWC https://paperswithcode.com/paper/tight-regret-bounds-for-bayesian-optimization
Repo
Framework

Neural Rendering and Reenactment of Human Actor Videos

Title Neural Rendering and Reenactment of Human Actor Videos
Authors Lingjie Liu, Weipeng Xu, Michael Zollhoefer, Hyeongwoo Kim, Florian Bernard, Marc Habermann, Wenping Wang, Christian Theobalt
Abstract We propose a method for generating video-realistic animations of real humans under user control. In contrast to conventional human character rendering, we do not require the availability of a production-quality photo-realistic 3D model of the human, but instead rely on a video sequence in conjunction with a (medium-quality) controllable 3D template model of the person. With that, our approach significantly reduces production cost compared to conventional rendering approaches based on production-quality 3D models, and can also be used to realistically edit existing videos. Technically, this is achieved by training a neural network that translates simple synthetic images of a human character into realistic imagery. For training our networks, we first track the 3D motion of the person in the video using the template model, and subsequently generate a synthetically rendered version of the video. These images are then used to train a conditional generative adversarial network that translates synthetic images of the 3D model into realistic imagery of the human. We evaluate our method for the reenactment of another person that is tracked in order to obtain the motion data, and show video results generated from artist-designed skeleton motion. Our results outperform the state-of-the-art in learning-based human image synthesis. Project page: http://gvv.mpi-inf.mpg.de/projects/wxu/HumanReenactment/
Tasks Image Generation
Published 2018-09-11
URL https://arxiv.org/abs/1809.03658v3
PDF https://arxiv.org/pdf/1809.03658v3.pdf
PWC https://paperswithcode.com/paper/neural-animation-and-reenactment-of-human
Repo
Framework

Uniform Convergence Bounds for Codec Selection

Title Uniform Convergence Bounds for Codec Selection
Authors Clayton Sanford, Cyrus Cousins, Eli Upfal
Abstract We frame the problem of selecting an optimal audio encoding scheme as a supervised learning task. Through uniform convergence theory, we guarantee approximately optimal codec selection while controlling for selection bias. We present rigorous statistical guarantees for the codec selection problem that hold for arbitrary distributions over audio sequences and for arbitrary quality metrics. Our techniques can thus balance sound quality and compression ratio, and use audio samples from the distribution to select a codec that performs well on that particular type of data. The applications of our technique are immense, as it can be used to optimize for quality and bandwidth usage of streaming and other digital media, while significantly outperforming approaches that apply a fixed codec to all data sources.
Tasks
Published 2018-12-18
URL http://arxiv.org/abs/1812.07568v1
PDF http://arxiv.org/pdf/1812.07568v1.pdf
PWC https://paperswithcode.com/paper/uniform-convergence-bounds-for-codec
Repo
Framework

Semantic Scene Completion Combining Colour and Depth: preliminary experiments

Title Semantic Scene Completion Combining Colour and Depth: preliminary experiments
Authors Andre Bernardes Soares Guedes, Teofilo Emidio de Campos, Adrian Hilton
Abstract Semantic scene completion is the task of producing a complete 3D voxel representation of volumetric occupancy with semantic labels for a scene from a single-view observation. We built upon the recent work of Song et al. (CVPR 2017), who proposed SSCnet, a method that performs scene completion and semantic labelling in a single end-to-end 3D convolutional network. SSCnet uses only depth maps as input, even though depth maps are usually obtained from devices that also capture colour information, such as RGBD sensors and stereo cameras. In this work, we investigate the potential of the RGB colour channels to improve SSCnet.
Tasks
Published 2018-02-13
URL http://arxiv.org/abs/1802.04735v1
PDF http://arxiv.org/pdf/1802.04735v1.pdf
PWC https://paperswithcode.com/paper/semantic-scene-completion-combining-colour
Repo
Framework

Mask R-CNN with Pyramid Attention Network for Scene Text Detection

Title Mask R-CNN with Pyramid Attention Network for Scene Text Detection
Authors Zhida Huang, Zhuoyao Zhong, Lei Sun, Qiang Huo
Abstract In this paper, we present a new Mask R-CNN based text detection approach which can robustly detect multi-oriented and curved text from natural scene images in a unified manner. To enhance the feature representation ability of Mask R-CNN for text detection tasks, we propose to use the Pyramid Attention Network (PAN) as a new backbone network of Mask R-CNN. Experiments demonstrate that PAN can suppress false alarms caused by text-like backgrounds more effectively. Our proposed approach has achieved superior performance on both multi-oriented (ICDAR-2015, ICDAR-2017 MLT) and curved (SCUT-CTW1500) text detection benchmark tasks by only using single-scale and single-model testing.
Tasks Curved Text Detection, Scene Text Detection
Published 2018-11-22
URL http://arxiv.org/abs/1811.09058v1
PDF http://arxiv.org/pdf/1811.09058v1.pdf
PWC https://paperswithcode.com/paper/mask-r-cnn-with-pyramid-attention-network-for
Repo
Framework
comments powered by Disqus