Paper Group ANR 1453
Coordinate-wise Armijo’s condition. Development of a classifiers/quantifiers dictionary towards French-Japanese MT. Spatial Influence-aware Reinforcement Learning for Intelligent Transportation System. A generic framework for task selection driven by synthetic emotions. Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs. Deep Learning to …
Coordinate-wise Armijo’s condition
| Title | Coordinate-wise Armijo’s condition |
| Authors | Tuyen Trung Truong |
| Abstract | Let $z=(x,y)$ be coordinates for the product space $\mathbb{R}^{m_1}\times \mathbb{R}^{m_2}$. Let $f:\mathbb{R}^{m_1}\times \mathbb{R}^{m_2}\rightarrow \mathbb{R}$ be a $C^1$ function, and $\nabla f=(\partial _xf,\partial _yf)$ its gradient. Fix $0<\alpha <1$. For a point $(x,y) \in \mathbb{R}^{m_1}\times \mathbb{R}^{m_2}$, a number $\delta >0$ satisfies Armijo’s condition at $(x,y)$ if the following inequality holds: \begin{eqnarray*} f(x-\delta \partial _xf,y-\delta \partial _yf)-f(x,y)\leq -\alpha \delta (\partial _xf^2+\partial _yf^2). \end{eqnarray*} When $f(x,y)=f_1(x)+f_2(y)$ is a coordinate-wise sum map, we propose the following {\bf coordinate-wise} Armijo’s condition. Fix again $0<\alpha <1$. A pair of positive numbers $\delta _1,\delta _2>0$ satisfies the coordinate-wise variant of Armijo’s condition at $(x,y)$ if the following inequality holds: \begin{eqnarray*} [f_1(x-\delta _1\nabla f_1(x))+f_2(y-\delta _2\nabla f_2(y))]-[f_1(x)+f_2(y)]\leq -\alpha (\delta _1\nabla f_1(x)^2+\delta _2\nabla f_2(y)^2). \end{eqnarray*} We then extend results in our recent previous results, on Backtracking Gradient Descent and some variants, to this setting. We show by an example the advantage of using coordinate-wise Armijo’s condition over the usual Armijo’s condition. |
| Tasks | |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07820v1 |
| https://arxiv.org/pdf/1911.07820v1.pdf | |
| PWC | https://paperswithcode.com/paper/coordinate-wise-armijos-condition |
| Repo | |
| Framework | |
Development of a classifiers/quantifiers dictionary towards French-Japanese MT
| Title | Development of a classifiers/quantifiers dictionary towards French-Japanese MT |
| Authors | Mutsuko Tomokiyo, Mathieu Mangeot, Christian Boitet |
| Abstract | Although classifiers/quantifiers (CQs) expressions appear frequently in everyday communications or written documents, they are described neither in classical bilingual paper dictionaries , nor in machine-readable dictionaries. The paper describes a CQs dictionary, edited from the corpus we have annotated, and its usage in the framework of French-Japanese machine translation (MT). CQs treatment in MT often causes problems of lexical ambiguity, polylexical phrase recognition difficulties in analysis and doubtful output in transfer-generation, in particular for distant languages pairs like French and Japanese. Our basic treatment of CQs is to annotate the corpus by UNL-UWs (Universal Networking Language-Universal words) 1 , and then to produce a bilingual or multilingual dictionary of CQs, based on synonymy through identity of UWs. |
| Tasks | Machine Translation |
| Published | 2019-02-21 |
| URL | http://arxiv.org/abs/1902.08061v1 |
| http://arxiv.org/pdf/1902.08061v1.pdf | |
| PWC | https://paperswithcode.com/paper/development-of-a-classifiersquantifiers |
| Repo | |
| Framework | |
Spatial Influence-aware Reinforcement Learning for Intelligent Transportation System
| Title | Spatial Influence-aware Reinforcement Learning for Intelligent Transportation System |
| Authors | Wenhang Bao, Xiao-yang Liu |
| Abstract | Intelligent transportation systems (ITSs) are envisioned to be crucial for smart cities, which aims at improving traffic flow to improve the life quality of urban residents and reducing congestion to improve the efficiency of commuting. However, several challenges need to be resolved before such systems can be deployed, for example, conventional solutions for Markov decision process (MDP) and single-agent Reinforcement Learning (RL) algorithms suffer from poor scalability, and multi-agent systems suffer from poor communication and coordination. In this paper, we explore the potential of mutual information sharing, or in other words, spatial influence based communication, to optimize traffic light control policy. First, we mathematically analyze the transportation system. We conclude that the transportation system does not have stationary Nash Equilibrium, thereby reinforcement learning algorithms offer suitable solutions. Secondly, we describe how to build a multi-agent Deep Deterministic Policy Gradient (DDPG) system with spatial influence and social group utility incorporated. Then we utilize the grid topology road network to empirically demonstrate the scalability of the new system. We demonstrate three types of directed communications to show the effect of directions of social influence on the entire network utility and individual utility. Lastly, we define “selfish index” and analyze the effect of it on total group utility. |
| Tasks | |
| Published | 2019-12-14 |
| URL | https://arxiv.org/abs/1912.06880v1 |
| https://arxiv.org/pdf/1912.06880v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-influence-aware-reinforcement |
| Repo | |
| Framework | |
A generic framework for task selection driven by synthetic emotions
| Title | A generic framework for task selection driven by synthetic emotions |
| Authors | Claudius Gros |
| Abstract | Given a certain complexity level, humanized agents may select from a wide range of possible tasks, with each activity corresponding to a transient goal. In general there will be no overarching credit assignment scheme allowing to compare available options with respect to expected utilities. For this situation we propose a task selection framework that is based on time allocation via emotional stationarity (TAES). Emotions are argued to correspond to abstract criteria, such as satisfaction, challenge and boredom, along which activities that have been carried out can be evaluated. The resulting timeline of experienced emotions is then compared with the `character’ of the agent, which is defined in terms of a preferred distribution of emotional states. The long-term goal of the agent, to align experience with character, is achieved by optimizing the frequency for selecting the individual tasks. Upon optimization, the statistics of emotion experience becomes stationary. | |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11700v1 |
| https://arxiv.org/pdf/1909.11700v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-generic-framework-for-task-selection-driven |
| Repo | |
| Framework | |
Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs
| Title | Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs |
| Authors | Dar Gilboa, Bo Chang, Minmin Chen, Greg Yang, Samuel S. Schoenholz, Ed H. Chi, Jeffrey Pennington |
| Abstract | Training recurrent neural networks (RNNs) on long sequence tasks is plagued with difficulties arising from the exponential explosion or vanishing of signals as they propagate forward or backward through the network. Many techniques have been proposed to ameliorate these issues, including various algorithmic and architectural modifications. Two of the most successful RNN architectures, the LSTM and the GRU, do exhibit modest improvements over vanilla RNN cells, but they still suffer from instabilities when trained on very long sequences. In this work, we develop a mean field theory of signal propagation in LSTMs and GRUs that enables us to calculate the time scales for signal propagation as well as the spectral properties of the state-to-state Jacobians. By optimizing these quantities in terms of the initialization hyperparameters, we derive a novel initialization scheme that eliminates or reduces training instabilities. We demonstrate the efficacy of our initialization scheme on multiple sequence tasks, on which it enables successful training while a standard initialization either fails completely or is orders of magnitude slower. We also observe a beneficial effect on generalization performance using this new initialization. |
| Tasks | |
| Published | 2019-01-25 |
| URL | https://arxiv.org/abs/1901.08987v2 |
| https://arxiv.org/pdf/1901.08987v2.pdf | |
| PWC | https://paperswithcode.com/paper/dynamical-isometry-and-a-mean-field-theory-of-1 |
| Repo | |
| Framework | |
Deep Learning to Predict Student Outcomes
| Title | Deep Learning to Predict Student Outcomes |
| Authors | Byung-Hak Kim |
| Abstract | The increasingly fast development cycle for online course contents, along with the diverse student demographics in each online classroom, make real-time student outcomes prediction an interesting topic for both industrial research and practical needs. In this paper, we tackle the problem of real-time student performance prediction in an on-going course using a domain adaptation framework. This framework is a system trained on labeled student outcome data from previous coursework but is meant to be deployed on another course. In particular, we introduce a GritNet architecture, and develop an unsupervised domain adaptation method to transfer a GritNet trained on a past course to a new course without any student outcome label. Our results for real Udacity student graduation predictions show that the GritNet not only generalizes well from one course to another across different Nanodegree programs, but also enhances real-time predictions explicitly in the first few weeks when accurate predictions are most challenging. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-04-27 |
| URL | http://arxiv.org/abs/1905.02530v1 |
| http://arxiv.org/pdf/1905.02530v1.pdf | |
| PWC | https://paperswithcode.com/paper/190502530 |
| Repo | |
| Framework | |
Randomized Exploration in Generalized Linear Bandits
| Title | Randomized Exploration in Generalized Linear Bandits |
| Authors | Branislav Kveton, Manzil Zaheer, Csaba Szepesvari, Lihong Li, Mohammad Ghavamzadeh, Craig Boutilier |
| Abstract | We study two randomized algorithms for generalized linear bandits, GLM-TSL and GLM-FPL. GLM-TSL samples a generalized linear model (GLM) from the Laplace approximation to the posterior distribution. GLM-FPL fits a GLM to a randomly perturbed history of past rewards. We prove $\tilde{O}(d \sqrt{n \log K})$ bounds on the $n$-round regret of GLM-TSL and GLM-FPL, where $d$ is the number of features and $K$ is the number of arms. The regret bound of GLM-TSL improves upon prior work and the regret bound of GLM-FPL is the first of its kind. We apply both GLM-TSL and GLM-FPL to logistic and neural network bandits, and show that they perform well empirically. In more complex models, GLM-FPL is significantly faster. Our results showcase the role of randomization, beyond sampling from the posterior, in exploration. |
| Tasks | |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.08947v2 |
| https://arxiv.org/pdf/1906.08947v2.pdf | |
| PWC | https://paperswithcode.com/paper/randomized-exploration-in-generalized-linear |
| Repo | |
| Framework | |
Analyzing Linguistic Complexity and Scientific Impact
| Title | Analyzing Linguistic Complexity and Scientific Impact |
| Authors | Chao Lu, Yi Bu, Xianlei Dong, Jie Wang, Ying Ding, Vincent Larivière, Cassidy R. Sugimoto, Logan Paul, Chengzhi Zhang |
| Abstract | The number of publications and the number of citations received have become the most common indicators of scholarly success. In this context, scientific writing increasingly plays an important role in scholars’ scientific careers. To understand the relationship between scientific writing and scientific impact, this paper selected 12 variables of linguistic complexity as a proxy for depicting scientific writing. We then analyzed these features from 36,400 full-text Biology articles and 1,797 full-text Psychology articles. These features were compared to the scientific impact of articles, grouped into high, medium, and low categories. The results suggested no practical significant relationship between linguistic complexity and citation strata in either discipline. This suggests that textual complexity plays little role in scientific impact in our data sets. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11843v1 |
| https://arxiv.org/pdf/1907.11843v1.pdf | |
| PWC | https://paperswithcode.com/paper/analyzing-linguistic-complexity-and |
| Repo | |
| Framework | |
A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions
| Title | A Case Study on Combining ASR and Visual Features for Generating Instructional Video Captions |
| Authors | Jack Hessel, Bo Pang, Zhenhai Zhu, Radu Soricut |
| Abstract | Instructional videos get high-traffic on video sharing platforms, and prior work suggests that providing time-stamped, subtask annotations (e.g., “heat the oil in the pan”) improves user experiences. However, current automatic annotation methods based on visual features alone perform only slightly better than constant prediction. Taking cues from prior work, we show that we can improve performance significantly by considering automatic speech recognition (ASR) tokens as input. Furthermore, jointly modeling ASR tokens and visual features results in higher performance compared to training individually on either modality. We find that unstated background information is better explained by visual features, whereas fine-grained distinctions (e.g., “add oil” vs. “add olive oil”) are disambiguated more easily via ASR tokens. |
| Tasks | Speech Recognition |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02930v1 |
| https://arxiv.org/pdf/1910.02930v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-case-study-on-combining-asr-and-visual |
| Repo | |
| Framework | |
Simultaneous Clustering and Optimization for Evolving Datasets
| Title | Simultaneous Clustering and Optimization for Evolving Datasets |
| Authors | Yawei Zhao, En Zhu, Xinwang Liu, Chang Tang, Deke Guo, Jianping Yin |
| Abstract | Simultaneous clustering and optimization (SCO) has recently drawn much attention due to its wide range of practical applications. Many methods have been previously proposed to solve this problem and obtain the optimal model. However, when a dataset evolves over time, those existing methods have to update the model frequently to guarantee accuracy; such updating is computationally infeasible. In this paper, we propose a new formulation of SCO to handle evolving datasets. Specifically, we propose a new variant of the alternating direction method of multipliers (ADMM) to solve this problem efficiently. The guarantee of model accuracy is analyzed theoretically for two specific tasks: ridge regression and convex clustering. Extensive empirical studies confirm the effectiveness of our method. |
| Tasks | |
| Published | 2019-08-04 |
| URL | https://arxiv.org/abs/1908.01384v1 |
| https://arxiv.org/pdf/1908.01384v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-clustering-and-optimization-for |
| Repo | |
| Framework | |
Road Surface Friction Prediction Using Long Short-Term Memory Neural Network Based on Historical Data
| Title | Road Surface Friction Prediction Using Long Short-Term Memory Neural Network Based on Historical Data |
| Authors | Ziyuan Pu, Shuo Wang, Chenglong Liu, Zhiyong Cui, Yinhai Wang |
| Abstract | Road surface friction significantly impacts traffic safety and mobility. A precise road surface friction prediction model can help to alleviate the influence of inclement road conditions on traffic safety, Level of Service, traffic mobility, fuel efficiency, and sustained economic productivity. Most related previous studies are laboratory-based methods that are difficult for practical implementation. Moreover, in other data-driven methods, the demonstrated time-series features of road surface conditions have not been considered. This study employed a Long-Short Term Memory (LSTM) neural network to develop a data-driven road surface friction prediction model based on historical data. The proposed prediction model outperformed the other baseline models in terms of the lowest value of predictive performance measurements. The influence of the number of time-lags and the predicting time interval on predictive accuracy was analyzed. In addition, the influence of adding road surface water thickness, road surface temperature and air temperature on predictive accuracy also were investigated. The findings of this study can support road maintenance strategy development and decision making, thus mitigating the impact of inclement road conditions on traffic mobility and safety. Future work includes a modified LSTM-based prediction model development by accommodating flexible time intervals between time-lags. |
| Tasks | Decision Making, Time Series |
| Published | 2019-11-01 |
| URL | https://arxiv.org/abs/1911.02372v1 |
| https://arxiv.org/pdf/1911.02372v1.pdf | |
| PWC | https://paperswithcode.com/paper/road-surface-friction-prediction-using-long |
| Repo | |
| Framework | |
Streaming Classification of Variable Stars
| Title | Streaming Classification of Variable Stars |
| Authors | Lukas Zorich, Karim Pichara, Pavlos Protopapas |
| Abstract | In the last years, automatic classification of variable stars has received substantial attention. Using machine learning techniques for this task has proven to be quite useful. Typically, machine learning classifiers used for this task require to have a fixed training set, and the training process is performed offline. Upcoming surveys such as the Large Synoptic Survey Telescope (LSST) will generate new observations daily, where an automatic classification system able to create alerts online will be mandatory. A system with those characteristics must be able to update itself incrementally. Unfortunately, after training, most machine learning classifiers do not support the inclusion of new observations in light curves, they need to re-train from scratch. Naively re-training from scratch is not an option in streaming settings, mainly because of the expensive pre-processing routines required to obtain a vector representation of light curves (features) each time we include new observations. In this work, we propose a streaming probabilistic classification model; it uses a set of newly designed features that work incrementally. With this model, we can have a machine learning classifier that updates itself in real time with new observations. To test our approach, we simulate a streaming scenario with light curves from CoRot, OGLE and MACHO catalogs. Results show that our model achieves high classification performance, staying an order of magnitude faster than traditional classification approaches. |
| Tasks | Classification Of Variable Stars |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02235v1 |
| https://arxiv.org/pdf/1912.02235v1.pdf | |
| PWC | https://paperswithcode.com/paper/streaming-classification-of-variable-stars |
| Repo | |
| Framework | |
Predicting Path Failure In Time-Evolving Graphs
| Title | Predicting Path Failure In Time-Evolving Graphs |
| Authors | Jia Li, Zhichao Han, Hong Cheng, Jiao Su, Pengyun Wang, Jianfeng Zhang, Lujia Pan |
| Abstract | In this paper we use a time-evolving graph which consists of a sequence of graph snapshots over time to model many real-world networks. We study the path classification problem in a time-evolving graph, which has many applications in real-world scenarios, for example, predicting path failure in a telecommunication network and predicting path congestion in a traffic network in the near future. In order to capture the temporal dependency and graph structure dynamics, we design a novel deep neural network named Long Short-Term Memory R-GCN (LRGCN). LRGCN considers temporal dependency between time-adjacent graph snapshots as a special relation with memory, and uses relational GCN to jointly process both intra-time and inter-time relations. We also propose a new path representation method named self-attentive path embedding (SAPE), to embed paths of arbitrary length into fixed-length vectors. Through experiments on a real-world telecommunication network and a traffic network in California, we demonstrate the superiority of LRGCN to other competing methods in path failure prediction, and prove the effectiveness of SAPE on path representation. |
| Tasks | |
| Published | 2019-05-10 |
| URL | https://arxiv.org/abs/1905.03994v2 |
| https://arxiv.org/pdf/1905.03994v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-path-failure-in-time-evolving |
| Repo | |
| Framework | |
Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
| Title | Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling |
| Authors | Cindy Trinh, Emilie Kaufmann, Claire Vernade, Richard Combes |
| Abstract | Stochastic Rank-One Bandits (Katarya et al, (2017a,b)) are a simple framework for regret minimization problems over rank-one matrices of arms. The initially proposed algorithms are proved to have logarithmic regret, but do not match the existing lower bound for this problem. We close this gap by first proving that rank-one bandits are a particular instance of unimodal bandits, and then providing a new analysis of Unimodal Thompson Sampling (UTS), initially proposed by Paladino et al (2017). We prove an asymptotically optimal regret bound on the frequentist regret of UTS and we support our claims with simulations showing the significant improvement of our method compared to the state-of-the-art. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.03074v1 |
| https://arxiv.org/pdf/1912.03074v1.pdf | |
| PWC | https://paperswithcode.com/paper/solving-bernoulli-rank-one-bandits-with |
| Repo | |
| Framework | |
Hand Orientation Estimation in Probability Density Form
| Title | Hand Orientation Estimation in Probability Density Form |
| Authors | Kazuaki Kondo, Daisuke Deguchi, Atsushi Shimada |
| Abstract | Hand orientation is an essential feature required to understand hand behaviors and subsequently support human activities. In this paper, we present a new method for estimating hand orientation in probability density form. It can solve the cyclicity problem in direct angular representation and enables the integration of multiple predictions based on different features. We validated the performance of the proposed method and an integration example using our dataset, which captured cooperative group work. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.04952v1 |
| https://arxiv.org/pdf/1906.04952v1.pdf | |
| PWC | https://paperswithcode.com/paper/hand-orientation-estimation-in-probability |
| Repo | |
| Framework | |
