Paper Group ANR 245
Interpretable Apprenticeship Learning with Temporal Logic Specifications. Binarsity: a penalization for one-hot encoded features in linear supervised learning. A Learning-Based Approach for Lane Departure Warning Systems with a Personalized Driver Model. Fast Model Identification via Physics Engines for Data-Efficient Policy Search. Introspection: …
Interpretable Apprenticeship Learning with Temporal Logic Specifications
| Title | Interpretable Apprenticeship Learning with Temporal Logic Specifications |
| Authors | Daniel Kasenberg, Matthias Scheutz |
| Abstract | Recent work has addressed using formulas in linear temporal logic (LTL) as specifications for agents planning in Markov Decision Processes (MDPs). We consider the inverse problem: inferring an LTL specification from demonstrated behavior trajectories in MDPs. We formulate this as a multiobjective optimization problem, and describe state-based (“what actually happened”) and action-based (“what the agent expected to happen”) objective functions based on a notion of “violation cost”. We demonstrate the efficacy of the approach by employing genetic programming to solve this problem in two simple domains. |
| Tasks | Multiobjective Optimization |
| Published | 2017-10-28 |
| URL | http://arxiv.org/abs/1710.10532v1 |
| http://arxiv.org/pdf/1710.10532v1.pdf | |
| PWC | https://paperswithcode.com/paper/interpretable-apprenticeship-learning-with |
| Repo | |
| Framework | |
Binarsity: a penalization for one-hot encoded features in linear supervised learning
| Title | Binarsity: a penalization for one-hot encoded features in linear supervised learning |
| Authors | Mokhtar Z. Alaya, Simon Bussy, Stéphane Gaïffas, Agathe Guilloux |
| Abstract | This paper deals with the problem of large-scale linear supervised learning in settings where a large number of continuous features are available. We propose to combine the well-known trick of one-hot encoding of continuous features with a new penalization called \emph{binarsity}. In each group of binary features coming from the one-hot encoding of a single raw continuous feature, this penalization uses total-variation regularization together with an extra linear constraint. This induces two interesting properties on the model weights of the one-hot encoded features: they are piecewise constant, and are eventually block sparse. Non-asymptotic oracle inequalities for generalized linear models are proposed. Moreover, under a sparse additive model assumption, we prove that our procedure matches the state-of-the-art in this setting. Numerical experiments illustrate the good performances of our approach on several datasets. It is also noteworthy that our method has a numerical complexity comparable to standard $\ell_1$ penalization. |
| Tasks | |
| Published | 2017-03-24 |
| URL | http://arxiv.org/abs/1703.08619v4 |
| http://arxiv.org/pdf/1703.08619v4.pdf | |
| PWC | https://paperswithcode.com/paper/binarsity-a-penalization-for-one-hot-encoded |
| Repo | |
| Framework | |
A Learning-Based Approach for Lane Departure Warning Systems with a Personalized Driver Model
| Title | A Learning-Based Approach for Lane Departure Warning Systems with a Personalized Driver Model |
| Authors | Wenshuo Wang, Ding Zhao, Junqiang Xi, Wei Han |
| Abstract | Misunderstanding of driver correction behaviors (DCB) is the primary reason for false warnings of lane-departure-prediction systems. We propose a learning-based approach to predicting unintended lane-departure behaviors (LDB) and the chance for drivers to bring the vehicle back to the lane. First, in this approach, a personalized driver model for lane-departure and lane-keeping behavior is established by combining the Gaussian mixture model and the hidden Markov model. Second, based on this model, we develop an online model-based prediction algorithm to predict the forthcoming vehicle trajectory and judge whether the driver will demonstrate an LDB or a DCB. We also develop a warning strategy based on the model-based prediction algorithm that allows the lane-departure warning system to be acceptable for drivers according to the predicted trajectory. In addition, the naturalistic driving data of 10 drivers is collected through the University of Michigan Safety Pilot Model Deployment program to train the personalized driver model and validate this approach. We compare the proposed method with a basic time-to-lane-crossing (TLC) method and a TLC-directional sequence of piecewise lateral slopes (TLC-DSPLS) method. The results show that the proposed approach can reduce the false-warning rate to 3.07%. |
| Tasks | |
| Published | 2017-02-04 |
| URL | http://arxiv.org/abs/1702.01228v1 |
| http://arxiv.org/pdf/1702.01228v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-learning-based-approach-for-lane-departure |
| Repo | |
| Framework | |
Fast Model Identification via Physics Engines for Data-Efficient Policy Search
| Title | Fast Model Identification via Physics Engines for Data-Efficient Policy Search |
| Authors | Shaojun Zhu, Andrew Kimmel, Kostas E. Bekris, Abdeslam Boularias |
| Abstract | This paper presents a method for identifying mechanical parameters of robots or objects, such as their mass and friction coefficients. Key features are the use of off-the-shelf physics engines and the adaptation of a Bayesian optimization technique towards minimizing the number of real-world experiments needed for model-based reinforcement learning. The proposed framework reproduces in a physics engine experiments performed on a real robot and optimizes the model’s mechanical parameters so as to match real-world trajectories. The optimized model is then used for learning a policy in simulation, before real-world deployment. It is well understood, however, that it is hard to exactly reproduce real trajectories in simulation. Moreover, a near-optimal policy can be frequently found with an imperfect model. Therefore, this work proposes a strategy for identifying a model that is just good enough to approximate the value of a locally optimal policy with a certain confidence, instead of wasting effort on identifying the most accurate model. Evaluations, performed both in simulation and on a real robotic manipulation task, indicate that the proposed strategy results in an overall time-efficient, integrated model identification and learning solution, which significantly improves the data-efficiency of existing policy search algorithms. |
| Tasks | |
| Published | 2017-10-24 |
| URL | http://arxiv.org/abs/1710.08893v3 |
| http://arxiv.org/pdf/1710.08893v3.pdf | |
| PWC | https://paperswithcode.com/paper/fast-model-identification-via-physics-engines |
| Repo | |
| Framework | |
Introspection: Accelerating Neural Network Training By Learning Weight Evolution
| Title | Introspection: Accelerating Neural Network Training By Learning Weight Evolution |
| Authors | Abhishek Sinha, Mausoom Sarkar, Aahitagni Mukherjee, Balaji Krishnamurthy |
| Abstract | Neural Networks are function approximators that have achieved state-of-the-art accuracy in numerous machine learning tasks. In spite of their great success in terms of accuracy, their large training time makes it difficult to use them for various tasks. In this paper, we explore the idea of learning weight evolution pattern from a simple network for accelerating training of novel neural networks. We use a neural network to learn the training pattern from MNIST classification and utilize it to accelerate training of neural networks used for CIFAR-10 and ImageNet classification. Our method has a low memory footprint and is computationally efficient. This method can also be used with other optimizers to give faster convergence. The results indicate a general trend in the weight evolution during training of neural networks. |
| Tasks | |
| Published | 2017-04-17 |
| URL | http://arxiv.org/abs/1704.04959v1 |
| http://arxiv.org/pdf/1704.04959v1.pdf | |
| PWC | https://paperswithcode.com/paper/introspection-accelerating-neural-network |
| Repo | |
| Framework | |
Continuum Limit of Posteriors in Graph Bayesian Inverse Problems
| Title | Continuum Limit of Posteriors in Graph Bayesian Inverse Problems |
| Authors | Nicolas Garcia Trillos, Daniel Sanz-Alonso |
| Abstract | We consider the problem of recovering a function input of a differential equation formulated on an unknown domain $M$. We assume to have access to a discrete domain $M_n={x_1, \dots, x_n} \subset M$, and to noisy measurements of the output solution at $p\le n$ of those points. We introduce a graph-based Bayesian inverse problem, and show that the graph-posterior measures over functions in $M_n$ converge, in the large $n$ limit, to a posterior over functions in $M$ that solves a Bayesian inverse problem with known domain. The proofs rely on the variational formulation of the Bayesian update, and on a new topology for the study of convergence of measures over functions on point clouds to a measure over functions on the continuum. Our framework, techniques, and results may serve to lay the foundations of robust uncertainty quantification of graph-based tasks in machine learning. The ideas are presented in the concrete setting of recovering the initial condition of the heat equation on an unknown manifold. |
| Tasks | |
| Published | 2017-06-22 |
| URL | http://arxiv.org/abs/1706.07193v1 |
| http://arxiv.org/pdf/1706.07193v1.pdf | |
| PWC | https://paperswithcode.com/paper/continuum-limit-of-posteriors-in-graph |
| Repo | |
| Framework | |
Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention
| Title | Japanese Sentiment Classification using a Tree-Structured Long Short-Term Memory with Attention |
| Authors | Ryosuke Miyazaki, Mamoru Komachi |
| Abstract | Previous approaches to training syntax-based sentiment classification models required phrase-level annotated corpora, which are not readily available in many languages other than English. Thus, we propose the use of tree-structured Long Short-Term Memory with an attention mechanism that pays attention to each subtree of the parse tree. Experimental results indicate that our model achieves the state-of-the-art performance in a Japanese sentiment classification task. |
| Tasks | Sentiment Analysis |
| Published | 2017-04-04 |
| URL | http://arxiv.org/abs/1704.00924v2 |
| http://arxiv.org/pdf/1704.00924v2.pdf | |
| PWC | https://paperswithcode.com/paper/japanese-sentiment-classification-using-a |
| Repo | |
| Framework | |
Symplectomorphic registration with phase space regularization by entropy spectrum pathways
| Title | Symplectomorphic registration with phase space regularization by entropy spectrum pathways |
| Authors | Vitaly L. Galinsky, Lawrence R. Frank |
| Abstract | The ability to register image data to a common coordinate system is a critical feature of virtually all imaging studies that require multiple subject analysis, combining single subject data from multiple modalities, or both. However, in spite of the abundance of literature on the subject and the existence of several variants of registration algorithms, their practical utility remains problematic, as commonly acknowledged even by developers of these methods because the complexity of the problem has resisted a general, flexible, and robust theoretical and computational framework. To address this issue, we present a new registration method that is similar in spirit to the current state-of-the-art technique of diffeomorphic mapping, but is more general and flexible. The method utilizes a Hamiltonian formalism and constructs registration as a sequence of symplectomorphic maps in conjunction with a novel phase space regularization based on the powerful entropy spectrum pathways (ESP) framework. The method is demonstrated on the three different magnetic resonance imaging (MRI) modalities routinely used for human neuroimaging applications by mapping between high resolution anatomical (HRA) volumes, medium resolution diffusion weighted MRI (DW-MRI) and HRA volumes, and low resolution functional MRI (fMRI) and HRA volumes. The typical processing time for high quality mapping ranges from less than a minute to several minutes on a modern multi core CPU for typical high resolution anatomical (~256x256x256 voxels) MRI volumes. |
| Tasks | |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.05105v1 |
| http://arxiv.org/pdf/1706.05105v1.pdf | |
| PWC | https://paperswithcode.com/paper/symplectomorphic-registration-with-phase |
| Repo | |
| Framework | |
Improved Algorithms for Matrix Recovery from Rank-One Projections
| Title | Improved Algorithms for Matrix Recovery from Rank-One Projections |
| Authors | Mohammadreza Soltani, Chinmay Hegde |
| Abstract | We consider the problem of estimation of a low-rank matrix from a limited number of noisy rank-one projections. In particular, we propose two fast, non-convex \emph{proper} algorithms for matrix recovery and support them with rigorous theoretical analysis. We show that the proposed algorithms enjoy linear convergence and that their sample complexity is independent of the condition number of the unknown true low-rank matrix. By leveraging recent advances in low-rank matrix approximation techniques, we show that our algorithms achieve computational speed-ups over existing methods. Finally, we complement our theory with some numerical experiments. |
| Tasks | |
| Published | 2017-05-21 |
| URL | http://arxiv.org/abs/1705.07469v1 |
| http://arxiv.org/pdf/1705.07469v1.pdf | |
| PWC | https://paperswithcode.com/paper/improved-algorithms-for-matrix-recovery-from |
| Repo | |
| Framework | |
Robustness Analysis of Visual QA Models by Basic Questions
| Title | Robustness Analysis of Visual QA Models by Basic Questions |
| Authors | Jia-Hong Huang, Cuong Duc Dao, Modar Alfadly, C. Huck Yang, Bernard Ghanem |
| Abstract | Visual Question Answering (VQA) models should have both high robustness and accuracy. Unfortunately, most of the current VQA research only focuses on accuracy because there is a lack of proper methods to measure the robustness of VQA models. There are two main modules in our algorithm. Given a natural language question about an image, the first module takes the question as input and then outputs the ranked basic questions, with similarity scores, of the main given question. The second module takes the main question, image and these basic questions as input and then outputs the text-based answer of the main question about the given image. We claim that a robust VQA model is one, whose performance is not changed much when related basic questions as also made available to it as input. We formulate the basic questions generation problem as a LASSO optimization, and also propose a large scale Basic Question Dataset (BQD) and Rscore (novel robustness measure), for analyzing the robustness of VQA models. We hope our BQD will be used as a benchmark for to evaluate the robustness of VQA models, so as to help the community build more robust and accurate VQA models. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2017-09-14 |
| URL | http://arxiv.org/abs/1709.04625v3 |
| http://arxiv.org/pdf/1709.04625v3.pdf | |
| PWC | https://paperswithcode.com/paper/robustness-analysis-of-visual-qa-models-by |
| Repo | |
| Framework | |
Wasserstein Identity Testing
| Title | Wasserstein Identity Testing |
| Authors | Shichuan Deng, Wenzheng Li, Xuan Wu |
| Abstract | Uniformity testing and the more general identity testing are well studied problems in distributional property testing. Most previous work focuses on testing under $L_1$-distance. However, when the support is very large or even continuous, testing under $L_1$-distance may require a huge (even infinite) number of samples. Motivated by such issues, we consider the identity testing in Wasserstein distance (a.k.a. transportation distance and earthmover distance) on a metric space (discrete or continuous). In this paper, we propose the Wasserstein identity testing problem (Identity Testing in Wasserstein distance). We obtain nearly optimal worst-case sample complexity for the problem. Moreover, for a large class of probability distributions satisfying the so-called “Doubling Condition”, we provide nearly instance-optimal sample complexity. |
| Tasks | |
| Published | 2017-10-28 |
| URL | http://arxiv.org/abs/1710.10457v1 |
| http://arxiv.org/pdf/1710.10457v1.pdf | |
| PWC | https://paperswithcode.com/paper/wasserstein-identity-testing |
| Repo | |
| Framework | |
Effective injury forecasting in soccer with GPS training data and machine learning
| Title | Effective injury forecasting in soccer with GPS training data and machine learning |
| Authors | Alessio Rossi, Luca Pappalardo, Paolo Cintia, Marcello Iaia, Javier Fernandez, Daniel Medina |
| Abstract | Injuries have a great impact on professional soccer, due to their large influence on team performance and the considerable costs of rehabilitation for players. Existing studies in the literature provide just a preliminary understanding of which factors mostly affect injury risk, while an evaluation of the potential of statistical models in forecasting injuries is still missing. In this paper, we propose a multi-dimensional approach to injury forecasting in professional soccer that is based on GPS measurements and machine learning. By using GPS tracking technology, we collect data describing the training workload of players in a professional soccer club during a season. We then construct an injury forecaster and show that it is both accurate and interpretable by providing a set of case studies of interest to soccer practitioners. Our approach opens a novel perspective on injury prevention, providing a set of simple and practical rules for evaluating and interpreting the complex relations between injury risk and training performance in professional soccer. |
| Tasks | |
| Published | 2017-05-23 |
| URL | http://arxiv.org/abs/1705.08079v2 |
| http://arxiv.org/pdf/1705.08079v2.pdf | |
| PWC | https://paperswithcode.com/paper/effective-injury-forecasting-in-soccer-with |
| Repo | |
| Framework | |
Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English
| Title | Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English |
| Authors | Duygu Ataman, Matteo Negri, Marco Turchi, Marcello Federico |
| Abstract | The necessity of using a fixed-size word vocabulary in order to control the model complexity in state-of-the-art neural machine translation (NMT) systems is an important bottleneck on performance, especially for morphologically rich languages. Conventional methods that aim to overcome this problem by using sub-word or character-level representations solely rely on statistics and disregard the linguistic properties of words, which leads to interruptions in the word structure and causes semantic and syntactic losses. In this paper, we propose a new vocabulary reduction method for NMT, which can reduce the vocabulary of a given input corpus at any rate while also considering the morphological properties of the language. Our method is based on unsupervised morphology learning and can be, in principle, used for pre-processing any language pair. We also present an alternative word segmentation method based on supervised morphological analysis, which aids us in measuring the accuracy of our model. We evaluate our method in Turkish-to-English NMT task where the input language is morphologically rich and agglutinative. We analyze different representation methods in terms of translation accuracy as well as the semantic and syntactic properties of the generated output. Our method obtains a significant improvement of 2.3 BLEU points over the conventional vocabulary reduction technique, showing that it can provide better accuracy in open vocabulary translation of morphologically rich languages. |
| Tasks | Machine Translation, Morphological Analysis |
| Published | 2017-07-31 |
| URL | http://arxiv.org/abs/1707.09879v1 |
| http://arxiv.org/pdf/1707.09879v1.pdf | |
| PWC | https://paperswithcode.com/paper/linguistically-motivated-vocabulary-reduction |
| Repo | |
| Framework | |
A Review of Neural Network Based Machine Learning Approaches for Rotor Angle Stability Control
| Title | A Review of Neural Network Based Machine Learning Approaches for Rotor Angle Stability Control |
| Authors | Reza Yousefian, Sukumar Kamalasadan |
| Abstract | This paper reviews the current status and challenges of Neural Networks (NNs) based machine learning approaches for modern power grid stability control including their design and implementation methodologies. NNs are widely accepted as Artificial Intelligence (AI) approaches offering an alternative way to control complex and ill-defined problems. In this paper various application of NNs for power system rotor angle stabilization and control problem is discussed. The main focus of this paper is on the use of Reinforcement Learning (RL) and Supervised Learning (SL) algorithms in power system wide-area control (WAC). Generally, these algorithms due to their capability in modeling nonlinearities and uncertainties are used for transient classification, neuro-control, wide-area monitoring and control, renewable energy management and control, and so on. The works of researchers in the field of conventional and renewable energy systems are reported and categorized. Paper concludes by presenting, comparing and evaluating various learning techniques and infrastructure configurations based on efficiency. |
| Tasks | |
| Published | 2017-01-05 |
| URL | http://arxiv.org/abs/1701.01214v1 |
| http://arxiv.org/pdf/1701.01214v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-review-of-neural-network-based-machine |
| Repo | |
| Framework | |
Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data
| Title | Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data |
| Authors | David Hallac, Sagar Vare, Stephen Boyd, Jure Leskovec |
| Abstract | Subsequence clustering of multivariate time series is a useful tool for discovering repeated patterns in temporal data. Once these patterns have been discovered, seemingly complicated datasets can be interpreted as a temporal sequence of only a small number of states, or clusters. For example, raw sensor data from a fitness-tracking application can be expressed as a timeline of a select few actions (i.e., walking, sitting, running). However, discovering these patterns is challenging because it requires simultaneous segmentation and clustering of the time series. Furthermore, interpreting the resulting clusters is difficult, especially when the data is high-dimensional. Here we propose a new method of model-based clustering, which we call Toeplitz Inverse Covariance-based Clustering (TICC). Each cluster in the TICC method is defined by a correlation network, or Markov random field (MRF), characterizing the interdependencies between different observations in a typical subsequence of that cluster. Based on this graphical representation, TICC simultaneously segments and clusters the time series data. We solve the TICC problem through alternating minimization, using a variation of the expectation maximization (EM) algorithm. We derive closed-form solutions to efficiently solve the two resulting subproblems in a scalable way, through dynamic programming and the alternating direction method of multipliers (ADMM), respectively. We validate our approach by comparing TICC to several state-of-the-art baselines in a series of synthetic experiments, and we then demonstrate on an automobile sensor dataset how TICC can be used to learn interpretable clusters in real-world scenarios. |
| Tasks | Time Series |
| Published | 2017-06-10 |
| URL | http://arxiv.org/abs/1706.03161v2 |
| http://arxiv.org/pdf/1706.03161v2.pdf | |
| PWC | https://paperswithcode.com/paper/toeplitz-inverse-covariance-based-clustering |
| Repo | |
| Framework | |
