January 31, 2020

3008 words 15 mins read

Paper Group ANR 183

Data Centers Job Scheduling with Deep Reinforcement Learning. Predicting Lake Erie Wave Heights using XGBoost. Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure. On Semi-Supervised Multiple Representation Behavior Learning. Verifying Robustness of Gradient Boosted Models. Solving Markov Decision Processes with …

Data Centers Job Scheduling with Deep Reinforcement Learning


Title	Data Centers Job Scheduling with Deep Reinforcement Learning
Authors	Sisheng Liang, Zhou Yang, Fang Jin, Yong Chen
Abstract	Efficient job scheduling on data centers under heterogeneous complexity is crucial but challenging since it involves the allocation of multi-dimensional resources over time and space. To adapt the complex computing environment in data centers, we proposed an innovative Advantage Actor-Critic (A2C) deep reinforcement learning based approach called A2cScheduler for job scheduling. A2cScheduler consists of two agents, one of which, dubbed the actor, is responsible for learning the scheduling policy automatically and the other one, the critic, reduces the estimation error. Unlike previous policy gradient approaches, A2cScheduler is designed to reduce the gradient estimation variance and to update parameters efficiently. We show that the A2cScheduler can achieve competitive scheduling performance using both simulated workloads and real data collected from an academic data center.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07820v2
PDF	https://arxiv.org/pdf/1909.07820v2.pdf
PWC	https://paperswithcode.com/paper/job-scheduling-on-data-centers-with-deep
Repo
Framework

Predicting Lake Erie Wave Heights using XGBoost


Title	Predicting Lake Erie Wave Heights using XGBoost
Authors	Haoguo Hu, Philip Chu
Abstract	Dangerous large wave put the coastal communities and vessels operating under threats and wave predictions are strongly needed for early warnings. While numerical wave models, such as WAVEWATCH III (WW3), are useful to provide spatially continuous information to supplement in situ observations, however, they often require intensive computational costs. An attractive alternative is machine-learning method, which can potentially provide comparable performance of numerical wave models but only requires a small fraction of computational costs. In this study, we applied and tested a novel machine learning method based on XGBoost for predicting waves in Lake Erie in 2016-2017. In this study, buoy data from 1994 to 2017 were processed for model training and testing. We trained the model with data from 1994-2015, then used the trained model to predict 2016 and 2017 wave features. The mean absolute error of wave height is about 0.11-0.18 m and the maximum error is 1.14-1.95 m, depending on location and year. For comparison, an unstructured WW3 model was implemented in Lake Erie for simulating wind generated waves. The WW3 results were compared with buoy data from National Data Buoy Center in Lake Erie, the mean absolute error of wave height is about 0.12-0.48 m and the maximum error is about 1.03-2.93 m. The results show that WW3 underestimates wave height spikes during strong wind events and The XGBoost improves prediction on wave height spikes. The XGBoost runs much faster than WW3. For a model year run on a supercomputer, WW3 needs 12 hours with 60 CPUs while XGBoost needs only 10 minutes with 1 CPU. In summary, the XGBoost provided comparable performance for our simulations in Lake Erie wave height and the computational time required was about 0.02 % of the numerical simulations.
Tasks
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01786v1
PDF	https://arxiv.org/pdf/1912.01786v1.pdf
PWC	https://paperswithcode.com/paper/predicting-lake-erie-wave-heights-using
Repo
Framework

Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure


Title	Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure
Authors	Guannan Qu, Na Li
Abstract	This paper considers a multi-agent Markov Decision Process (MDP), where there are $n$ agents and each agent $i$ is associated with a state $s_i$ and action $a_i$ taking values from a finite set. Though the global state space size and action space size are exponential in $n$, we impose local dependence structures and focus on local policies that only depend on local states, and we propose a method that finds nearly optimal local policies in polynomial time (in $n$) when the dependence structure is a one directional tree. The algorithm builds on approximated reward functions which are evaluated using locally truncated Markov process. Further, under some special conditions, we prove that the gap between the approximated reward function and the true reward function is decaying exponentially fast as the length of the truncated Markov process gets longer. The intuition behind this is that under some assumptions, the effect of agent interactions decays exponentially in the distance between agents, which we term “fast decaying property”.
Tasks
Published	2019-09-15
URL	https://arxiv.org/abs/1909.06900v1
PDF	https://arxiv.org/pdf/1909.06900v1.pdf
PWC	https://paperswithcode.com/paper/exploiting-fast-decaying-and-locality-in
Repo
Framework

On Semi-Supervised Multiple Representation Behavior Learning


Title	On Semi-Supervised Multiple Representation Behavior Learning
Authors	Ruqian Lu, Shengluan Hou
Abstract	We propose a novel paradigm of semi-supervised learning (SSL)–the semi-supervised multiple representation behavior learning (SSMRBL). SSMRBL aims to tackle the difficulty of learning a grammar for natural language parsing where the data are natural language texts and the ‘labels’ for marking data are parsing trees and/or grammar rule pieces. We call such ‘labels’ as compound structured labels which require a hard work for training. SSMRBL is an incremental learning process that can learn more than one representation, which is an appropriate solution for dealing with the scarce of labeled training data in the age of big data and with the heavy workload of learning compound structured labels. We also present a typical example of SSMRBL, regarding behavior learning in form of a grammatical approach towards domain-based multiple text summarization (DBMTS). DBMTS works under the framework of rhetorical structure theory (RST). SSMRBL includes two representations: text embedding (for representing information contained in the texts) and grammar model (for representing parsing as a behavior). The first representation was learned as embedded digital vectors called impacts in a low dimensional space. The grammar model was learned in an iterative way. Then an automatic domain-oriented multi-text summarization approach was proposed based on the two representations discussed above. Experimental results on large-scale Chinese dataset SogouCA indicate that the proposed method brings a good performance even if only few labeled texts are used for training with respect to our defined automated metrics.
Tasks	Text Summarization
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09292v1
PDF	https://arxiv.org/pdf/1910.09292v1.pdf
PWC	https://paperswithcode.com/paper/on-semi-supervised-multiple-representation
Repo
Framework

Verifying Robustness of Gradient Boosted Models


Title	Verifying Robustness of Gradient Boosted Models
Authors	Gil Einziger, Maayan Goldstein, Yaniv Sa’ar, Itai Segall
Abstract	Gradient boosted models are a fundamental machine learning technique. Robustness to small perturbations of the input is an important quality measure for machine learning models, but the literature lacks a method to prove the robustness of gradient boosted models. This work introduces VeriGB, a tool for quantifying the robustness of gradient boosted models. VeriGB encodes the model and the robustness property as an SMT formula, which enables state of the art verification tools to prove the model’s robustness. We extensively evaluate VeriGB on publicly available datasets and demonstrate a capability for verifying large models. Finally, we show that some model configurations tend to be inherently more robust than others.
Tasks
Published	2019-06-26
URL	https://arxiv.org/abs/1906.10991v1
PDF	https://arxiv.org/pdf/1906.10991v1.pdf
PWC	https://paperswithcode.com/paper/verifying-robustness-of-gradient-boosted
Repo
Framework

Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times


Title	Solving Markov Decision Processes with Reachability Characterization from Mean First Passage Times
Authors	Shoubhik Debnath, Lantao Liu, Gaurav Sukhatme
Abstract	A new mechanism for efficiently solving the Markov decision processes (MDPs) is proposed in this paper. We introduce the notion of reachability landscape where we use the Mean First Passage Time (MFPT) as a means to characterize the reachability of every state in the state space. We show that such reachability characterization very well assesses the importance of states and thus provides a natural basis for effectively prioritizing states and approximating policies. Built on such a novel observation, we design two new algorithms – Mean First Passage Time based Value Iteration (MFPT-VI) and Mean First Passage Time based Policy Iteration (MFPT-PI) – that have been modified from the state-of-the-art solution methods. To validate our design, we have performed numerical evaluations in robotic decision-making scenarios, by comparing the proposed new methods with corresponding classic baseline mechanisms. The evaluation results showed that MFPT-VI and MFPT-PI have outperformed the state-of-the-art solutions in terms of both practical runtime and number of iterations. Aside from the advantage of fast convergence, this new solution method is intuitively easy to understand and practically simple to implement.
Tasks	Decision Making
Published	2019-01-04
URL	http://arxiv.org/abs/1901.01229v1
PDF	http://arxiv.org/pdf/1901.01229v1.pdf
PWC	https://paperswithcode.com/paper/solving-markov-decision-processes-with
Repo
Framework

Knowledge-guided Unsupervised Rhetorical Parsing for Text Summarization


Title	Knowledge-guided Unsupervised Rhetorical Parsing for Text Summarization
Authors	Shengluan Hou, Ruqian Lu
Abstract	Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, attentional encoder-decoder model for rhetorical parsing and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods.
Tasks	Representation Learning, Text Summarization
Published	2019-10-14
URL	https://arxiv.org/abs/1910.05915v1
PDF	https://arxiv.org/pdf/1910.05915v1.pdf
PWC	https://paperswithcode.com/paper/knowledge-guided-unsupervised-rhetorical
Repo
Framework

Clustering without Over-Representation


Title	Clustering without Over-Representation
Authors	Sara Ahmadian, Alessandro Epasto, Ravi Kumar, Mohammad Mahdian
Abstract	In this paper we consider clustering problems in which each point is endowed with a color. The goal is to cluster the points to minimize the classical clustering cost but with the additional constraint that no color is over-represented in any cluster. This problem is motivated by practical clustering settings, e.g., in clustering news articles where the color of an article is its source, it is preferable that no single news source dominates any cluster. For the most general version of this problem, we obtain an algorithm that has provable guarantees of performance; our algorithm is based on finding a fractional solution using a linear program and rounding the solution subsequently. For the special case of the problem where no color has an absolute majority in any cluster, we obtain a simpler combinatorial algorithm also with provable guarantees. Experiments on real-world data shows that our algorithms are effective in finding good clustering without over-representation.
Tasks
Published	2019-05-29
URL	https://arxiv.org/abs/1905.12753v1
PDF	https://arxiv.org/pdf/1905.12753v1.pdf
PWC	https://paperswithcode.com/paper/clustering-without-over-representation
Repo
Framework

Position Paper: Towards Transparent Machine Learning


Title	Position Paper: Towards Transparent Machine Learning
Authors	Dustin Juliano
Abstract	Transparent machine learning is introduced as an alternative form of machine learning, where both the model and the learning system are represented in source code form. The goal of this project is to enable direct human understanding of machine learning models, giving us the ability to learn, verify, and refine them as programs. If solved, this technology could represent a best-case scenario for the safety and security of AI systems going forward.
Tasks
Published	2019-11-12
URL	https://arxiv.org/abs/1911.06612v1
PDF	https://arxiv.org/pdf/1911.06612v1.pdf
PWC	https://paperswithcode.com/paper/position-paper-towards-transparent-machine
Repo
Framework

Automatic crack detection and classification by exploiting statistical event descriptors for Deep Learning


Title	Automatic crack detection and classification by exploiting statistical event descriptors for Deep Learning
Authors	Giulio Siracusano, Aurelio La Corte, Riccardo Tomasello, Francesco Lamonaca, Carmelo Scuro, Francesca Garescì, Mario Carpentieri, Giovanni Finocchio
Abstract	In modern building infrastructures, the chance to devise adaptive and unsupervised data-driven health monitoring systems is gaining in popularity due to the large availability of data from low-cost sensors with internetworking capabilities. In particular, deep learning provides the tools for processing and analyzing this unprecedented amount of data efficiently. The main purpose of this paper is to combine the recent advances of Deep Learning (DL) and statistical analysis on structural health monitoring (SHM) to develop an accurate classification tool able to discriminate among different acoustic emission events (cracks) by means of the identification of tensile, shear and mixed modes. The applications of DL in SHM systems is described by using the concept of Bidirectional Long Short Term Memory. We investigated on effective event descriptors to capture the unique characteristics from the different types of modes. Among them, Spectral Kurtosis and Spectral L2/L1 Norm exhibit distinctive behavior and effectively contributed to the learning process. This classification will contribute to unambiguously detect incipient damages, which is advantageous to realize predictive maintenance. Tests on experimental results confirm that this method achieves accurate classification (92%) capabilities of crack events and can impact on the design of future SHM technologies.
Tasks
Published	2019-07-24
URL	https://arxiv.org/abs/1907.10709v1
PDF	https://arxiv.org/pdf/1907.10709v1.pdf
PWC	https://paperswithcode.com/paper/automatic-crack-detection-and-classification
Repo
Framework

Online Anomaly Detection with Sparse Gaussian Processes


Title	Online Anomaly Detection with Sparse Gaussian Processes
Authors	Jingjing Fei, Shiliang Sun
Abstract	Online anomaly detection of time-series data is an important and challenging task in machine learning. Gaussian processes (GPs) are powerful and flexible models for modeling time-series data. However, the high time complexity of GPs limits their applications in online anomaly detection. Attributed to some internal or external changes, concept drift usually occurs in time-series data, where the characteristics of data and meanings of abnormal behaviors alter over time. Online anomaly detection methods should have the ability to adapt to concept drift. Motivated by the above facts, this paper proposes the method of sparse Gaussian processes with Q-function (SGP-Q). The SGP-Q employs sparse Gaussian processes (SGPs) whose time complexity is lower than that of GPs, thus significantly speeding up online anomaly detection. By using Q-function properly, the SGP-Q can adapt to concept drift well. Moreover, the SGP-Q makes use of few abnormal data in the training data by its strategy of updating training data, resulting in more accurate sparse Gaussian process regression models and better anomaly detection results. We evaluate the SGP-Q on various artificial and real-world datasets. Experimental results validate the effectiveness of the SGP-Q.
Tasks	Anomaly Detection, Gaussian Processes, Time Series
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05761v1
PDF	https://arxiv.org/pdf/1905.05761v1.pdf
PWC	https://paperswithcode.com/paper/online-anomaly-detection-with-sparse-gaussian
Repo
Framework

3D Face Reconstruction Using Color Photometric Stereo with Uncalibrated Near Point Lights


Title	3D Face Reconstruction Using Color Photometric Stereo with Uncalibrated Near Point Lights
Authors	Zhang Chen, Yu Ji, Mingyuan Zhou, Sing Bing Kang, Jingyi Yu
Abstract	We present a new color photometric stereo (CPS) method that recovers high quality, detailed 3D face geometry in a single shot. Our system uses three uncalibrated near point lights of different colors and a single camera. For robust self-calibration of the light sources, we use 3D morphable model (3DMM) and semantic segmentation of facial parts. We address the spectral ambiguity problem by incorporating albedo consensus, albedo similarity, and proxy prior into a unified framework. We avoid the need for spatial constancy of albedo; instead, we use a new measure for albedo similarity that is based on the albedo norm profile. Experiments show that our new approach produces state-of-the-art results from single image with high-fidelity geometry that includes details such as wrinkles.
Tasks	3D Face Reconstruction, Calibration, Face Reconstruction, Semantic Segmentation
Published	2019-04-04
URL	https://arxiv.org/abs/1904.02605v2
PDF	https://arxiv.org/pdf/1904.02605v2.pdf
PWC	https://paperswithcode.com/paper/3d-face-reconstruction-using-color
Repo
Framework

Bayesian Optimization using Deep Gaussian Processes


Title	Bayesian Optimization using Deep Gaussian Processes
Authors	Ali Hebbal, Loic Brevault, Mathieu Balesdent, El-Ghazali Talbi, Nouredine Melab
Abstract	Bayesian Optimization using Gaussian Processes is a popular approach to deal with the optimization of expensive black-box functions. However, because of the a priori on the stationarity of the covariance matrix of classic Gaussian Processes, this method may not be adapted for non-stationary functions involved in the optimization problem. To overcome this issue, a new Bayesian Optimization approach is proposed. It is based on Deep Gaussian Processes as surrogate models instead of classic Gaussian Processes. This modeling technique increases the power of representation to capture the non-stationarity by simply considering a functional composition of stationary Gaussian Processes, providing a multiple layer structure. This paper proposes a new algorithm for Global Optimization by coupling Deep Gaussian Processes and Bayesian Optimization. The specificities of this optimization method are discussed and highlighted with academic test cases. The performance of the proposed algorithm is assessed on analytical test cases and an aerospace design optimization problem and compared to the state-of-the-art stationary and non-stationary Bayesian Optimization approaches.
Tasks	Gaussian Processes
Published	2019-05-07
URL	https://arxiv.org/abs/1905.03350v1
PDF	https://arxiv.org/pdf/1905.03350v1.pdf
PWC	https://paperswithcode.com/paper/190503350
Repo
Framework

Exploring Semantic Segmentation on the DCT Representation


Title	Exploring Semantic Segmentation on the DCT Representation
Authors	Shao-Yuan Lo, Hsueh-Ming Hang
Abstract	Typical convolutional networks are trained and conducted on RGB images. However, images are often compressed for memory savings and efficient transmission in real-world applications. In this paper, we explore methods for performing semantic segmentation on the discrete cosine transform (DCT) representation defined by the JPEG standard. We first rearrange the DCT coefficients to form a preferred input type, then we tailor an existing network to the DCT inputs. The proposed method has an accuracy close to the RGB model at about the same network complexity. Moreover, we investigate the impact of selecting different DCT components on segmentation performance. With a proper selection, one can achieve the same level accuracy using only 36% of the DCT coefficients. We further show the robustness of our method under the quantization errors. To our knowledge, this paper is the first to explore semantic segmentation on the DCT representation.
Tasks	Quantization, Semantic Segmentation
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10015v2
PDF	https://arxiv.org/pdf/1907.10015v2.pdf
PWC	https://paperswithcode.com/paper/exploring-semantic-segmentation-on-the-dct
Repo
Framework

Ethics of Artificial Intelligence Demarcations


Title	Ethics of Artificial Intelligence Demarcations
Authors	Anders Braarud Hanssen, Stefano Nichele
Abstract	In this paper we present a set of key demarcations, particularly important when discussing ethical and societal issues of current AI research and applications. Properly distinguishing issues and concerns related to Artificial General Intelligence and weak AI, between symbolic and connectionist AI, AI methods, data and applications are prerequisites for an informed debate. Such demarcations would not only facilitate much-needed discussions on ethics on current AI technologies and research. In addition sufficiently establishing such demarcations would also enhance knowledge-sharing and support rigor in interdisciplinary research between technical and social sciences.
Tasks
Published	2019-04-23
URL	https://arxiv.org/abs/1904.10239v2
PDF	https://arxiv.org/pdf/1904.10239v2.pdf
PWC	https://paperswithcode.com/paper/ethics-of-artificial-intelligence
Repo
Framework