January 30, 2020

3264 words 16 mins read

Paper Group ANR 425

Learning to Have an Ear for Face Super-Resolution. Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks. Vulnerability Analysis for Data Driven Pricing Schemes. Coresets for Data-efficient Training of Machine Learning Models. Learning to Reuse Translations: Guiding Neural Machine Translation with Examples. KFHE-HO …

Learning to Have an Ear for Face Super-Resolution


Title	Learning to Have an Ear for Face Super-Resolution
Authors	Givi Meishvili, Simon Jenni, Paolo Favaro
Abstract	We propose a novel method to use both audio and a low-resolution image to perform extreme face super-resolution (a 16x increase of the input size). When the resolution of the input image is very low (e.g., 8x8 pixels), the loss of information is so dire that important details of the original identity have been lost and audio can aid the recovery of a plausible high-resolution image. In fact, audio carries information about facial attributes, such as gender and age. Moreover, if an audio track belongs to an identity in a known training set, such audio might even help to restore the original identity. Towards this goal, we propose a model and a training procedure to extract information about the face of a person from her audio track and to combine it with the information extracted from her low-resolution image, which relates more to pose and colors of the face. We demonstrate that the combination of these two inputs yields high-resolution images that better capture the correct attributes of the face. In particular, we show experimentally that audio can assist in recovering attributes such as the gender, the age and the identity, and thus improve the correctness of the image reconstruction process. Our procedure does not make use of human annotation and thus can be easily trained with existing video datasets. Moreover, we show that our model builds a factorized representation of images and audio as it allows one to mix low-resolution images and audio from different videos and to generate realistic faces with semantically meaningful combinations.
Tasks	Audio Super-Resolution, Face Reconstruction, Image Reconstruction, Super-Resolution
Published	2019-09-27
URL	https://arxiv.org/abs/1909.12780v2
PDF	https://arxiv.org/pdf/1909.12780v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-have-an-ear-for-face-super
Repo
Framework

Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks


Title	Deep Learning based Wireless Resource Allocation with Application to Vehicular Networks
Authors	Le Liang, Hao Ye, Guanding Yu, Geoffrey Ye Li
Abstract	It has been a long-held belief that judicious resource allocation is critical to mitigating interference, improving network efficiency, and ultimately optimizing wireless communication performance. The traditional wisdom is to explicitly formulate resource allocation as an optimization problem and then exploit mathematical programming to solve the problem to a certain level of optimality. Nonetheless, as wireless networks become increasingly diverse and complex, e.g., in the high-mobility vehicular networks, the current design methodologies face significant challenges and thus call for rethinking of the traditional design philosophy. Meanwhile, deep learning, with many success stories in various disciplines, represents a promising alternative due to its remarkable power to leverage data for problem solving. In this paper, we discuss the key motivations and roadblocks of using deep learning for wireless resource allocation with application to vehicular networks. We review major recent studies that mobilize the deep learning philosophy in wireless resource allocation and achieve impressive results. We first discuss deep learning assisted optimization for resource allocation. We then highlight the deep reinforcement learning approach to address resource allocation problems that are difficult to handle in the traditional optimization framework. We also identify some research directions that deserve further investigation.
Tasks
Published	2019-07-07
URL	https://arxiv.org/abs/1907.03289v2
PDF	https://arxiv.org/pdf/1907.03289v2.pdf
PWC	https://paperswithcode.com/paper/deep-learning-based-wireless-resource
Repo
Framework

Vulnerability Analysis for Data Driven Pricing Schemes


Title	Vulnerability Analysis for Data Driven Pricing Schemes
Authors	Jingshi Cui, Haoxiang Wang, Chenye Wu, Yang Yu
Abstract	Data analytics and machine learning techniques are being rapidly adopted into the power system, including power system control as well as electricity market design. In this paper, from an adversarial machine learning point of view, we examine the vulnerability of data-driven electricity market design. More precisely, we follow the idea that consumer’s load profile should uniquely determine its electricity rate, which yields a clustering oriented pricing scheme. We first identify the strategic behaviors of malicious users by defining a notion of disguising. Based on this notion, we characterize the sensitivity zones to evaluate the percentage of malicious users in each cluster. Based on a thorough cost benefit analysis, we conclude with the vulnerability analysis.
Tasks
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07453v1
PDF	https://arxiv.org/pdf/1911.07453v1.pdf
PWC	https://paperswithcode.com/paper/vulnerability-analysis-for-data-driven
Repo
Framework

Coresets for Data-efficient Training of Machine Learning Models


Title	Coresets for Data-efficient Training of Machine Learning Models
Authors	Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec
Abstract	Incremental gradient (IG) methods, such as stochastic gradient descent and its variants are commonly used for large scale optimization in machine learning. Despite the sustained effort to make IG methods more data-efficient, it remains an open question how to select a training data subset that can theoretically and practically perform on par with the full dataset. Here we develop CRAIG, a method to select a weighted subset (or coreset) of training data that closely estimates the full gradient by maximizing a submodular function. We prove that applying IG to this subset is guaranteed to converge to the (near)optimal solution with the same convergence rate as that of IG for convex optimization. As a result, CRAIG achieves a speedup that is inversely proportional to the size of the subset. To our knowledge, this is the first rigorous method for data-efficient training of general machine learning models. Our extensive set of experiments show that CRAIG, while achieving practically the same solution, speeds up various IG methods by up to 6x for logistic regression and 3x for training deep neural networks.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.01827v2
PDF	https://arxiv.org/pdf/1906.01827v2.pdf
PWC	https://paperswithcode.com/paper/data-sketching-for-faster-training-of-machine
Repo
Framework

Learning to Reuse Translations: Guiding Neural Machine Translation with Examples


Title	Learning to Reuse Translations: Guiding Neural Machine Translation with Examples
Authors	Qian Cao, Shaohui Kuang, Deyi Xiong
Abstract	In this paper, we study the problem of enabling neural machine translation (NMT) to reuse previous translations from similar examples in target prediction. Distinguishing reusable translations from noisy segments and learning to reuse them in NMT are non-trivial. To solve these challenges, we propose an Example-Guided NMT (EGNMT) framework with two models: (1) a noise-masked encoder model that masks out noisy words according to word alignments and encodes the noise-masked sentences with an additional example encoder and (2) an auxiliary decoder model that predicts reusable words via an auxiliary decoder sharing parameters with the primary decoder. We define and implement the two models with the state-of-the-art Transformer. Experiments show that the noise-masked encoder model allows NMT to learn useful information from examples with low fuzzy match scores (FMS) while the auxiliary decoder model is good for high-FMS examples. More experiments on Chinese-English, English-German and English-Spanish translation demonstrate that the combination of the two EGNMT models can achieve improvements of up to +9 BLEU points over the baseline system and +7 BLEU points over a two-encoder Transformer.
Tasks	Machine Translation
Published	2019-11-25
URL	https://arxiv.org/abs/1911.10732v2
PDF	https://arxiv.org/pdf/1911.10732v2.pdf
PWC	https://paperswithcode.com/paper/learning-to-reuse-translations-guiding-neural
Repo
Framework

KFHE-HOMER: A multi-label ensemble classification algorithm exploiting sensor fusion properties of the Kalman filter


Title	KFHE-HOMER: A multi-label ensemble classification algorithm exploiting sensor fusion properties of the Kalman filter
Authors	Arjun Pakrashi, Brian Mac Namee
Abstract	Multi-label classification allows a datapoint to be labelled with more than one class at the same time. In spite of their success in multi-class classification problems, ensemble methods based on approaches other than bagging have not been widely explored for multi-label classification problems. The Kalman Filter-based Heuristic Ensemble (KFHE) is a recent ensemble method that exploits the sensor fusion properties of the Kalman filter to combine several classifier models, and that has been shown to be very effective. This article proposes KFHE-HOMER, an extension of the KFHE ensemble approach to the multi-label domain. KFHE-HOMER sequentially trains multiple HOMER multi-label classifiers and aggregates their outputs using the sensor fusion properties of the Kalman filter. Experiments described in this article show that KFHE-HOMER performs consistently better than existing multi-label methods including existing approaches based on ensembles.
Tasks	Multi-Label Classification, Sensor Fusion
Published	2019-04-23
URL	https://arxiv.org/abs/1904.10552v2
PDF	https://arxiv.org/pdf/1904.10552v2.pdf
PWC	https://paperswithcode.com/paper/kfhe-homer-kalman-filter-based-heuristic
Repo
Framework


Title	The Commute Trip Sharing Problem
Authors	Mohd Hafiz Hasan, Pascal Van Hentenryck, Antoine Legrain
Abstract	Parking pressure has been steadily increasing in cities as well as in university and corporate campuses. To relieve this pressure, this paper studies a car-pooling platform that would match riders and drivers, while guaranteeing a ride back and exploiting spatial and temporal locality. In particular, the paper formalizes the Commute Trip Sharing Problem (CTSP) to find a routing plan that maximizes ride sharing for a set of commute trips. The CTSP is a generalization of the vehicle routing problem with routes that satisfy time window, capacity, pairing, precedence, ride duration, and driver constraints. The paper introduces two exact algorithms for the CTPS: A route-enumeration algorithm and a branch-and-price algorithm. Experimental results show that, on a high-fidelity, real-world dataset of commute trips from a mid-size city, both algorithms optimally solve small and medium-sized problems and produce high-quality solutions for larger problem instances. The results show that car pooling, if widely adopted, has the potential to reduce vehicle usage by up to 57% and decrease vehicle miles traveled by up to 46% while only incurring a 22% increase in average ride time per commuter for the trips considered.
Tasks
Published	2019-04-24
URL	https://arxiv.org/abs/1904.11017v2
PDF	https://arxiv.org/pdf/1904.11017v2.pdf
PWC	https://paperswithcode.com/paper/the-commute-trip-sharing-problem
Repo
Framework

Adaptive Discrete Smoothing for High-Dimensional and Nonlinear Panel Data


Title	Adaptive Discrete Smoothing for High-Dimensional and Nonlinear Panel Data
Authors	Xi Chen, Ye Luo, Martin Spindler
Abstract	In this paper we develop a data-driven smoothing technique for high-dimensional and non-linear panel data models. We allow for individual specific (non-linear) functions and estimation with econometric or machine learning methods by using weighted observations from other individuals. The weights are determined by a data-driven way and depend on the similarity between the corresponding functions and are measured based on initial estimates. The key feature of such a procedure is that it clusters individuals based on the distance / similarity between them, estimated in a first stage. Our estimation method can be combined with various statistical estimation procedures, in particular modern machine learning methods which are in particular fruitful in the high-dimensional case and with complex, heterogeneous data. The approach can be interpreted as a \textquotedblleft soft-clustering\textquotedblright\ in comparison to traditional\textquotedblleft\ hard clustering\textquotedblright that assigns each individual to exactly one group. We conduct a simulation study which shows that the prediction can be greatly improved by using our estimator. Finally, we analyze a big data set from didichuxing.com, a leading company in transportation industry, to analyze and predict the gap between supply and demand based on a large set of covariates. Our estimator clearly performs much better in out-of-sample prediction compared to existing linear panel data estimators.
Tasks
Published	2019-12-30
URL	https://arxiv.org/abs/1912.12867v2
PDF	https://arxiv.org/pdf/1912.12867v2.pdf
PWC	https://paperswithcode.com/paper/adaptive-discrete-smoothing-for-high
Repo
Framework

Lightweight and Scalable Particle Tracking and Motion Clustering of 3D Cell Trajectories


Title	Lightweight and Scalable Particle Tracking and Motion Clustering of 3D Cell Trajectories
Authors	Mojtaba S. Fazli, Rachel V. Stadler, BahaaEddin Alaila, Stephen A. Vella, Silvia N. J. Moreno, Gary E. Ward, Shannon Quinn
Abstract	Tracking cell particles in 3D microscopy videos is a challenging task but is of great significance for modeling the motion of cells. Proper characterization of the cell’s shape, evolution, and their movement over time is crucial to understanding and modeling the mechanobiology of cell migration in many diseases. One in particular, toxoplasmosis is the disease caused by the parasite Toxoplasma gondii. Roughly, one-third of the world’s population tests positive for T. gondii. Its virulence is linked to its lytic cycle, predicated on its motility and ability to enter and exit nucleated cells; therefore, studies elucidating its motility patterns are critical to the eventual development of therapeutic strategies. Here, we present a computational framework for fast and scalable detection, tracking, and identification of T. gondii motion phenotypes in 3D videos, in a completely unsupervised fashion. Our pipeline consists of several different modules including preprocessing, sparsification, cell detection, cell tracking, trajectories extraction, parametrization of the trajectories; and finally, a clustering step. Additionally, we identified the computational bottlenecks, and developed a lightweight and highly scalable pipeline through a combination of task distribution and parallelism. Our results prove both the accuracy and performance of our method.
Tasks
Published	2019-08-10
URL	https://arxiv.org/abs/1908.03775v2
PDF	https://arxiv.org/pdf/1908.03775v2.pdf
PWC	https://paperswithcode.com/paper/lightweight-and-scalable-particle-tracking
Repo
Framework

Convolutional Neural Network and decision support in medical imaging: case study of the recognition of blood cell subtypes


Title	Convolutional Neural Network and decision support in medical imaging: case study of the recognition of blood cell subtypes
Authors	Daouda Diouf, Djibril Seck, Mountaga Diop, Abdoulye Ba
Abstract	Identifying and characterizing the patient’s blood samples is indispensable in diagnostics of malignance suspicious. A painstaking and sometimes subjective task is used in laboratories to manually classify white blood cells. Neural mathematical methods as deep learnings can be very useful in the automated recognition of blood cells. This study uses a particular type of deep learning i.e., convolutional neural networks (CNNs or ConvNets) for image recognition of the four (4) blood cell types (neutrophil, eosinophil, lymphocyte and monocyte) and to enable it to tag them employing a dataset of blood cells with labels for the corresponding cell types. The elements of the database are the input of our CNN and they allowed us to create learning models for the image recognition/classification of the blood cells. We evaluated the recognition performance and outputs learned by the networks in order to implement a neural image recognition model capable of distinguishing polynuclear cells (neutrophil and eosinophil) from those of mononuclear cells (lymphocyte and monocyte). The validation accuracy is 97.77%.
Tasks
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08010v1
PDF	https://arxiv.org/pdf/1911.08010v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-neural-network-and-decision
Repo
Framework

EBBIOT: A Low-complexity Tracking Algorithm for Surveillance in IoVT Using Stationary Neuromorphic Vision Sensors


Title	EBBIOT: A Low-complexity Tracking Algorithm for Surveillance in IoVT Using Stationary Neuromorphic Vision Sensors
Authors	Jyotibdha Acharya, Andres Ussa Caycedo, Vandana Reddy Padala, Rishi Raj Sidhu Singh, Garrick Orchard, Bharath Ramesh, Arindam Basu
Abstract	In this paper, we present EBBIOT-a novel paradigm for object tracking using stationary neuromorphic vision sensors in low-power sensor nodes for the Internet of Video Things (IoVT). Different from fully event based tracking or fully frame based approaches, we propose a mixed approach where we create event-based binary images (EBBI) that can use memory efficient noise filtering algorithms. We exploit the motion triggering aspect of neuromorphic sensors to generate region proposals based on event density counts with >1000X less memory and computes compared to frame based approaches. We also propose a simple overlap based tracker (OT) with prediction based handling of occlusion. Our overall approach requires 7X less memory and 3X less computations than conventional noise filtering and event based mean shift (EBMS) tracking. Finally, we show that our approach results in significantly higher precision and recall compared to EBMS approach as well as Kalman Filter tracker when evaluated over 1.1 hours of traffic recordings at two different locations.
Tasks	Object Tracking
Published	2019-10-04
URL	https://arxiv.org/abs/1910.01851v1
PDF	https://arxiv.org/pdf/1910.01851v1.pdf
PWC	https://paperswithcode.com/paper/ebbiot-a-low-complexity-tracking-algorithm
Repo
Framework

LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks


Title	LeanResNet: A Low-cost Yet Effective Convolutional Residual Networks
Authors	Jonathan Ephrath, Lars Ruthotto, Eldad Haber, Eran Treister
Abstract	Convolutional Neural Networks (CNNs) filter the input data using spatial convolution operators with compact stencils. Commonly, the convolution operators couple features from all channels, which leads to immense computational cost in the training of and prediction with CNNs. To improve the efficiency of CNNs, we introduce lean convolution operators that reduce the number of parameters and computational complexity, and can be used in a wide range of existing CNNs. Here, we exemplify their use in residual networks (ResNets), which have been very reliable for a few years now and analyzed intensively. In our experiments on three image classification problems, the proposed LeanResNet yields results that are comparable to other recently proposed reduced architectures using similar number of parameters.
Tasks	Image Classification
Published	2019-04-15
URL	https://arxiv.org/abs/1904.06952v2
PDF	https://arxiv.org/pdf/1904.06952v2.pdf
PWC	https://paperswithcode.com/paper/leanresnet-a-low-cost-yet-effective
Repo
Framework

SylNet: An Adaptable End-to-End Syllable Count Estimator for Speech


Title	SylNet: An Adaptable End-to-End Syllable Count Estimator for Speech
Authors	Shreyas Seshadri, Okko Räsänen
Abstract	Automatic syllable count estimation (SCE) is used in a variety of applications ranging from speaking rate estimation to detecting social activity from wearable microphones or developmental research concerned with quantifying speech heard by language-learning children in different environments. The majority of previously utilized SCE methods have relied on heuristic DSP methods, and only a small number of bi-directional long short-term memory (BLSTM) approaches have made use of modern machine learning approaches in the SCE task. This paper presents a novel end-to-end method called SylNet for automatic syllable counting from speech, built on the basis of a recent developments in neural network architectures. We describe how the entire model can be optimized directly to minimize SCE error on the training data without annotations aligned at the syllable level, and how it can be adapted to new languages using limited speech data with known syllable counts. Experiments on several different languages reveal that SylNet generalizes to languages beyond its training data and further improves with adaptation. It also outperforms several previously proposed methods for syllabification, including end-to-end BLSTMs.
Tasks
Published	2019-06-24
URL	https://arxiv.org/abs/1906.09825v1
PDF	https://arxiv.org/pdf/1906.09825v1.pdf
PWC	https://paperswithcode.com/paper/sylnet-an-adaptable-end-to-end-syllable-count
Repo
Framework

Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices


Title	Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Suffices
Authors	Santosh S. Vempala, Andre Wibisono
Abstract	We study the Unadjusted Langevin Algorithm (ULA) for sampling from a probability distribution $\nu = e^{-f}$ on $\mathbb{R}^n$. We prove a convergence guarantee in Kullback-Leibler (KL) divergence assuming $\nu$ satisfies a log-Sobolev inequality and the Hessian of $f$ is bounded. Notably, we do not assume convexity or bounds on higher derivatives. We also prove convergence guarantees in R'enyi divergence of order $q > 1$ assuming the limit of ULA satisfies either the log-Sobolev or Poincar'e inequality.
Tasks
Published	2019-03-20
URL	https://arxiv.org/abs/1903.08568v3
PDF	https://arxiv.org/pdf/1903.08568v3.pdf
PWC	https://paperswithcode.com/paper/rapid-convergence-of-the-unadjusted-langevin
Repo
Framework

Sparse Optimization on General Atomic Sets: Greedy and Forward-Backward Algorithms


Title	Sparse Optimization on General Atomic Sets: Greedy and Forward-Backward Algorithms
Authors	Thomas Zhang
Abstract	We consider the problem of sparse atomic optimization, where the notion of “sparsity” is generalized to meaning some linear combination of few atoms. The definition of atomic set is very broad; popular examples include the standard basis, low-rank matrices, overcomplete dictionaries, permutation matrices, orthogonal matrices, etc. The model of sparse atomic optimization therefore includes problems coming from many fields, including statistics, signal processing, machine learning, computer vision and so on. Specifically, we consider the problem of maximizing a restricted strongly convex (or concave), smooth function restricted to a sparse linear combination of atoms. We extend recent work that establish linear convergence rates of greedy algorithms on restricted strongly concave, smooth functions on sparse vectors to the realm of general atomic sets, where the convergence rate involves a novel quantity: the “sparse atomic condition number”. This leads to the strongest known multiplicative approximation guarantees for various flavors of greedy algorithms for sparse atomic optimization; in particular, we show that in many settings of interest the greedy algorithm can attain strong approximation guarantees while maintaining sparsity. Furthermore, we introduce a scheme for forward-backward algorithms that achieves the same approximation guarantees. Secondly, we define an alternate notion of weak submodularity, which we show is tightly related to the more familiar version that has been used to prove earlier linear convergence rates. We prove analogous multiplicative approximation guarantees using this alternate weak submodularity, and establish its distinct identity and applications.
Tasks
Published	2019-12-26
URL	https://arxiv.org/abs/1912.11931v1
PDF	https://arxiv.org/pdf/1912.11931v1.pdf
PWC	https://paperswithcode.com/paper/sparse-optimization-on-general-atomic-sets
Repo
Framework