January 28, 2020

2927 words 14 mins read

Paper Group ANR 821

Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis. E-HBA: Using Action Policies for Expert Advice and Agent Typification. Reinforcement Learning Driven Heuristic Optimization. A Novel Trend Symbolic Aggregate Approximation for Time Series. Granular Motor State Monitoring of Free Living Parkinson’s …

Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis


Title	Generic Bounds on the Maximum Deviations in Sequential Prediction: An Information-Theoretic Analysis
Authors	Song Fang, Quanyan Zhu
Abstract	In this paper, we derive generic bounds on the maximum deviations in prediction errors for sequential prediction via an information-theoretic approach. The fundamental bounds are shown to depend only on the conditional entropy of the data point to be predicted given the previous data points. In the asymptotic case, the bounds are achieved if and only if the prediction error is white and uniformly distributed.
Tasks
Published	2019-10-11
URL	https://arxiv.org/abs/1910.06742v2
PDF	https://arxiv.org/pdf/1910.06742v2.pdf
PWC	https://paperswithcode.com/paper/generic-bounds-on-the-maximum-deviations-in
Repo
Framework

E-HBA: Using Action Policies for Expert Advice and Agent Typification


Title	E-HBA: Using Action Policies for Expert Advice and Agent Typification
Authors	Stefano V. Albrecht, Jacob W. Crandall, Subramanian Ramamoorthy
Abstract	Past research has studied two approaches to utilise predefined policy sets in repeated interactions: as experts, to dictate our own actions, and as types, to characterise the behaviour of other agents. In this work, we bring these complementary views together in the form of a novel meta-algorithm, called Expert-HBA (E-HBA), which can be applied to any expert algorithm that considers the average (or total) payoff an expert has yielded in the past. E-HBA gradually mixes the past payoff with a predicted future payoff, which is computed using the type-based characterisation. We present results from a comprehensive set of repeated matrix games, comparing the performance of several well-known expert algorithms with and without the aid of E-HBA. Our results show that E-HBA has the potential to significantly improve the performance of expert algorithms.
Tasks
Published	2019-07-23
URL	https://arxiv.org/abs/1907.09810v1
PDF	https://arxiv.org/pdf/1907.09810v1.pdf
PWC	https://paperswithcode.com/paper/e-hba-using-action-policies-for-expert-advice
Repo
Framework

Reinforcement Learning Driven Heuristic Optimization


Title	Reinforcement Learning Driven Heuristic Optimization
Authors	Qingpeng Cai, Will Hang, Azalia Mirhoseini, George Tucker, Jingtao Wang, Wei Wei
Abstract	Heuristic algorithms such as simulated annealing, Concorde, and METIS are effective and widely used approaches to find solutions to combinatorial optimization problems. However, they are limited by the high sample complexity required to reach a reasonable solution from a cold-start. In this paper, we introduce a novel framework to generate better initial solutions for heuristic algorithms using reinforcement learning (RL), named RLHO. We augment the ability of heuristic algorithms to greedily improve upon an existing initial solution generated by RL, and demonstrate novel results where RL is able to leverage the performance of heuristics as a learning signal to generate better initialization. We apply this framework to Proximal Policy Optimization (PPO) and Simulated Annealing (SA). We conduct a series of experiments on the well-known NP-complete bin packing problem, and show that the RLHO method outperforms our baselines. We show that on the bin packing problem, RL can learn to help heuristics perform even better, allowing us to combine the best parts of both approaches.
Tasks	Combinatorial Optimization
Published	2019-06-16
URL	https://arxiv.org/abs/1906.06639v1
PDF	https://arxiv.org/pdf/1906.06639v1.pdf
PWC	https://paperswithcode.com/paper/reinforcement-learning-driven-heuristic
Repo
Framework

A Novel Trend Symbolic Aggregate Approximation for Time Series


Title	A Novel Trend Symbolic Aggregate Approximation for Time Series
Authors	Yufeng Yu, Yuelong Zhu, Dingsheng Wan, Qun Zhao, Huan Liu
Abstract	Symbolic Aggregate approximation (SAX) is a classical symbolic approach in many time series data mining applications. However, SAX only reflects the segment mean value feature and misses important information in a segment, namely the trend of the value change in the segment. Such a miss may cause a wrong classification in some cases, since the SAX representation cannot distinguish different time series with similar average values but different trends. In this paper, we present Trend Feature Symbolic Aggregate approximation (TFSAX) to solve this problem. First, we utilize Piecewise Aggregate Approximation (PAA) approach to reduce dimensionality and discretize the mean value of each segment by SAX. Second, extract trend feature in each segment by using trend distance factor and trend shape factor. Then, design multi-resolution symbolic mapping rules to discretize trend information into symbols. We also propose a modified distance measure by integrating the SAX distance with a weighted trend distance. We show that our distance measure has a tighter lower bound to the Euclidean distance than that of the original SAX. The experimental results on diverse time series data sets demonstrate that our proposed representation significantly outperforms the original SAX representation and an improved SAX representation for classification.
Tasks	Time Series
Published	2019-05-01
URL	http://arxiv.org/abs/1905.00421v1
PDF	http://arxiv.org/pdf/1905.00421v1.pdf
PWC	https://paperswithcode.com/paper/a-novel-trend-symbolic-aggregate
Repo
Framework

Granular Motor State Monitoring of Free Living Parkinson’s Disease Patients via Deep Learning


Title	Granular Motor State Monitoring of Free Living Parkinson’s Disease Patients via Deep Learning
Authors	Kamer A. Yuksel, Jann Goschenhofer, Hridya V. Varma, Urban Fietzek, Franz M. J. Pfister
Abstract	Parkinson’s disease (PD) is the second most common neurodegenerative disease worldwide and affects around 1% of the (60+ years old) elderly population in industrial nations. More than 80% of PD patients suffer from motor symptoms, which could be well addressed if a personalized medication schedule and dosage could be administered to them. However, such personalized medication schedule requires a continuous, objective and precise measurement of motor symptoms experienced by the patients during their regular daily activities. In this work, we propose the use of a wrist-worn smart-watch, which is equipped with 3D motion sensors, for estimating the motor fluctuation severity of PD patients in a free-living environment. We introduce a novel network architecture, a post-training scheme and a custom loss function that accounts for label noise to improve the results of our previous work in this domain and to establish a novel benchmark for nine-level PD motor state estimation.
Tasks
Published	2019-11-15
URL	https://arxiv.org/abs/1911.06913v2
PDF	https://arxiv.org/pdf/1911.06913v2.pdf
PWC	https://paperswithcode.com/paper/granular-motor-state-monitoring-of-free
Repo
Framework

Causal Discovery with Reinforcement Learning


Title	Causal Discovery with Reinforcement Learning
Authors	Shengyu Zhu, Ignavier Ng, Zhitang Chen
Abstract	Discovering causal structure among a set of variables is a fundamental problem in many empirical sciences. Traditional score-based casual discovery methods rely on various local heuristics to search for a Directed Acyclic Graph (DAG) according to a predefined score function. While these methods, e.g., greedy equivalence search, may have attractive results with infinite samples and certain model assumptions, they are usually less satisfactory in practice due to finite data and possible violation of assumptions. Motivated by recent advances in neural combinatorial optimization, we propose to use Reinforcement Learning (RL) to search for the DAG with the best scoring. Our encoder-decoder model takes observable data as input and generates graph adjacency matrices that are used to compute rewards. The reward incorporates both the predefined score function and two penalty terms for enforcing acyclicity. In contrast with typical RL applications where the goal is to learn a policy, we use RL as a search strategy and our final output would be the graph, among all graphs generated during training, that achieves the best reward. We conduct experiments on both synthetic and real datasets, and show that the proposed approach not only has an improved search ability but also allows a flexible score function under the acyclicity constraint.
Tasks	Causal Discovery, Combinatorial Optimization
Published	2019-06-11
URL	https://arxiv.org/abs/1906.04477v3
PDF	https://arxiv.org/pdf/1906.04477v3.pdf
PWC	https://paperswithcode.com/paper/causal-discovery-with-reinforcement-learning
Repo
Framework

Resolving Overlapping Convex Objects in Silhouette Images by Concavity Analysis and Gaussian Process


Title	Resolving Overlapping Convex Objects in Silhouette Images by Concavity Analysis and Gaussian Process
Authors	Sahar Zafari, Mariia Murashkina, Tuomas Eerola, Jouni Sampo, Heikki Kälviäinen, Heikki Haario
Abstract	Segmentation of overlapping convex objects has various applications, for example, in nanoparticles and cell imaging. Often the segmentation method has to rely purely on edges between the background and foreground making the analyzed images essentially silhouette images. Therefore, to segment the objects, the method needs to be able to resolve the overlaps between multiple objects by utilizing prior information about the shape of the objects. This paper introduces a novel method for segmentation of clustered partially overlapping convex objects in silhouette images. The proposed method involves three main steps: pre-processing, contour evidence extraction, and contour estimation. Contour evidence extraction starts by recovering contour segments from a binarized image by detecting concave points. After this, the contour segments which belong to the same objects are grouped. The grouping is formulated as a combinatorial optimization problem and solved using the branch and bound algorithm. Finally, the full contours of the objects are estimated by a Gaussian process regression method. The experiments on a challenging dataset consisting of nanoparticles demonstrate that the proposed method outperforms three current state-of-art approaches in overlapping convex objects segmentation. The method relies only on edge information and can be applied to any segmentation problems where the objects are partially overlapping and have a convex shape.
Tasks	Combinatorial Optimization
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01049v1
PDF	https://arxiv.org/pdf/1906.01049v1.pdf
PWC	https://paperswithcode.com/paper/resolving-overlapping-convex-objects-in
Repo
Framework

Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification


Title	Attention Deep Model with Multi-Scale Deep Supervision for Person Re-Identification
Authors	Di Wu, Chao Wang, Yong Wu, De-Shuang Huang
Abstract	In recent years, person re-identification (PReID) has become a hot topic in computer vision duo to it is an important part in intelligent surveillance. Many state-of-the-art PReID methods are attention-based or multi-scale feature learning deep models. However, introducing attention mechanism may lead to some important feature information losing issue. Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network. To address these issue, in this study, we introduce an attention deep architecture with multi-scale deep supervision for PReID. Technically, we contribute a reverse attention block to complement the attention block, and a novel multi-scale layer with deep supervision operator for training the backbone network. The proposed block and operator are only used for training, and discard in test phase. Experiments have been performed on Market-1501, DukeMTMC-reID and CUHK03 datasets. All the experiment results show that the proposed model significantly outperforms the other competitive state-of-the-art methods.
Tasks	Person Re-Identification
Published	2019-11-23
URL	https://arxiv.org/abs/1911.10335v2
PDF	https://arxiv.org/pdf/1911.10335v2.pdf
PWC	https://paperswithcode.com/paper/attention-deep-model-with-multi-scale-deep
Repo
Framework

Few-Shot Classification on Unseen Domains by Learning Disparate Modulators


Title	Few-Shot Classification on Unseen Domains by Learning Disparate Modulators
Authors	Yongseok Choi, Junyoung Park, Subin Yi, Dong-Yeon Cho
Abstract	Although few-shot learning studies have advanced rapidly with the help of meta-learning, their practical applicability is still limited because most of them assumed that all meta-training and meta-testing examples came from the same domain. Leveraging meta-learning on multiple heterogeneous domains, we propose a few-shot classification method which adapts to novel domains as well as novel classes, which is believed to be more practical in the real world. To address this challenging problem, we start from building a pool of multiple embedding models. Inspired by multi-task learning techniques, we design each model to have its own per-layer modulator with a base network shared by others. This allows the pool to have representational diversity as a whole without losing beneficial domain-invariant features. Experimental results show that our framework can be utilized effectively for few-shot learning on unseen domains by learning to select the best model or averaging all models in the pool. Additionally, ours outperform previous methods in few-shot classification tasks on multiple seen domains.
Tasks	Few-Shot Learning, Meta-Learning, Multi-Task Learning
Published	2019-09-11
URL	https://arxiv.org/abs/1909.04999v1
PDF	https://arxiv.org/pdf/1909.04999v1.pdf
PWC	https://paperswithcode.com/paper/few-shot-classification-on-unseen-domains-by
Repo
Framework

Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection


Title	Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection
Authors	Seijoon Kim, Seongsik Park, Byunggook Na, Sungroh Yoon
Abstract	Over the past decade, deep neural networks (DNNs) have demonstrated remarkable performance in a variety of applications. As we try to solve more advanced problems, increasing demands for computing and power resources has become inevitable. Spiking neural networks (SNNs) have attracted widespread interest as the third-generation of neural networks due to their event-driven and low-powered nature. SNNs, however, are difficult to train, mainly owing to their complex dynamics of neurons and non-differentiable spike operations. Furthermore, their applications have been limited to relatively simple tasks such as image classification. In this study, we investigate the performance degradation of SNNs in a more challenging regression problem (i.e., object detection). Through our in-depth analysis, we introduce two novel methods: channel-wise normalization and signed neuron with imbalanced threshold, both of which provide fast and accurate information transmission for deep SNNs. Consequently, we present a first spiked-based object detection model, called Spiking-YOLO. Our experiments show that Spiking-YOLO achieves remarkable results that are comparable (up to 98%) to those of Tiny YOLO on non-trivial datasets, PASCAL VOC and MS COCO. Furthermore, Spiking-YOLO on a neuromorphic chip consumes approximately 280 times less energy than Tiny YOLO and converges 2.3 to 4 times faster than previous SNN conversion methods.
Tasks	Image Classification, Object Detection, Real-Time Object Detection
Published	2019-03-12
URL	https://arxiv.org/abs/1903.06530v2
PDF	https://arxiv.org/pdf/1903.06530v2.pdf
PWC	https://paperswithcode.com/paper/spiking-yolo-spiking-neural-network-for-real
Repo
Framework

Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training


Title	Improving Variational Autoencoder with Deep Feature Consistent and Generative Adversarial Training
Authors	Xianxu Hou, Ke Sun, Linlin Shen, Guoping Qiu
Abstract	We present a new method for improving the performances of variational autoencoder (VAE). In addition to enforcing the deep feature consistent principle thus ensuring the VAE output and its corresponding input images to have similar deep features, we also implement a generative adversarial training mechanism to force the VAE to output realistic and natural images. We present experimental results to show that the VAE trained with our new method outperforms state of the art in generating face images with much clearer and more natural noses, eyes, teeth, hair textures as well as reasonable backgrounds. We also show that our method can learn powerful embeddings of input face images, which can be used to achieve facial attribute manipulation. Moreover we propose a multi-view feature extraction strategy to extract effective image representations, which can be used to achieve state of the art performance in facial attribute prediction.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01984v1
PDF	https://arxiv.org/pdf/1906.01984v1.pdf
PWC	https://paperswithcode.com/paper/improving-variational-autoencoder-with-deep
Repo
Framework

FMRI data augmentation via synthesis


Title	FMRI data augmentation via synthesis
Authors	Peiye Zhuang, Alexander G. Schwing, Sanmi Koyejo
Abstract	We present an empirical evaluation of fMRI data augmentation via synthesis. For synthesis we use generative mod-els trained on real neuroimaging data to produce novel task-dependent functional brain images. Analyzed generative mod-els include classic approaches such as the Gaussian mixture model (GMM), and modern implicit generative models such as the generative adversarial network (GAN) and the variational auto-encoder (VAE). In particular, the proposed GAN and VAE models utilize 3-dimensional convolutions, which enables modeling of high-dimensional brain image tensors with structured spatial correlations. The synthesized datasets are then used to augment classifiers designed to predict cognitive and behavioural outcomes. Our results suggest that the proposed models are able to generate high-quality synthetic brain images which are diverse and task-dependent. Perhaps most importantly, the performance improvements of data aug-mentation via synthesis are shown to be complementary to the choice of the predictive model. Thus, our results suggest that data augmentation via synthesis is a promising approach to address the limited availability of fMRI data, and to improve the quality of predictive fMRI models.
Tasks	Data Augmentation
Published	2019-07-13
URL	https://arxiv.org/abs/1907.06134v1
PDF	https://arxiv.org/pdf/1907.06134v1.pdf
PWC	https://paperswithcode.com/paper/fmri-data-augmentation-via-synthesis
Repo
Framework

A framework for anomaly detection using language modeling, and its applications to finance


Title	A framework for anomaly detection using language modeling, and its applications to finance
Authors	Armineh Nourbakhsh, Grace Bang
Abstract	In the finance sector, studies focused on anomaly detection are often associated with time-series and transactional data analytics. In this paper, we lay out the opportunities for applying anomaly and deviation detection methods to text corpora and challenges associated with them. We argue that language models that use distributional semantics can play a significant role in advancing these studies in novel directions, with new applications in risk identification, predictive modeling, and trend analysis.
Tasks	Anomaly Detection, Language Modelling, Time Series
Published	2019-08-24
URL	https://arxiv.org/abs/1908.09156v1
PDF	https://arxiv.org/pdf/1908.09156v1.pdf
PWC	https://paperswithcode.com/paper/a-framework-for-anomaly-detection-using
Repo
Framework

Supervised and unsupervised neural approaches to text readability


Title	Supervised and unsupervised neural approaches to text readability
Authors	Matej Martinc, Senja Pollak, Marko Robnik-Šikonja
Abstract	We present a set of novel neural supervised and unsupervised approaches for determining readability of documents. In the unsupervised setting, we leverage neural language models, while in the supervised setting three different neural architectures are tested in the classification setting. We show that the proposed neural unsupervised approach on average produces better results than traditional readability formulas and is transferable across languages. Employing neural classifiers, we outperform current state-of-the-art classification approaches to readability which rely on standard machine learning classifiers and extensive feature engineering. We tested several properties of the proposed approaches and showed their strengths and possibilities for improvements.
Tasks	Feature Engineering
Published	2019-07-26
URL	https://arxiv.org/abs/1907.11779v2
PDF	https://arxiv.org/pdf/1907.11779v2.pdf
PWC	https://paperswithcode.com/paper/supervised-and-unsupervised-neural-approaches
Repo
Framework

A sparse semismooth Newton based proximal majorization-minimization algorithm for nonconvex square-root-loss regression problems


Title	A sparse semismooth Newton based proximal majorization-minimization algorithm for nonconvex square-root-loss regression problems
Authors	Peipei Tang, Chengjing Wang, Defeng Sun, Kim-Chuan Toh
Abstract	In this paper, we consider high-dimensional nonconvex square-root-loss regression problems and introduce a proximal majorization-minimization (PMM) algorithm for these problems. Our key idea for making the proposed PMM to be efficient is to develop a sparse semismooth Newton method to solve the corresponding subproblems. By using the Kurdyka-{\L}ojasiewicz property exhibited in the underlining problems, we prove that the PMM algorithm converges to a d-stationary point. We also analyze the oracle property of the initial subproblem used in our algorithm. Extensive numerical experiments are presented to demonstrate the high efficiency of the proposed PMM algorithm.
Tasks
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11460v2
PDF	http://arxiv.org/pdf/1903.11460v2.pdf
PWC	https://paperswithcode.com/paper/a-sparse-semismooth-newton-based-proximal
Repo
Framework