Paper Group ANR 57
Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption. Accent Classification with Phonetic Vowel Representation. Towards reducing the multidimensionality of OLAP cubes using the Evolutionary Algorithms and Factor Analysis Methods. Crowd collectiveness measure via graph-based node clique lear …
Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption
| Title | Projected Semi-Stochastic Gradient Descent Method with Mini-Batch Scheme under Weak Strong Convexity Assumption |
| Authors | Jie Liu, Martin Takac |
| Abstract | We propose a projected semi-stochastic gradient descent method with mini-batch for improving both the theoretical complexity and practical performance of the general stochastic gradient descent method (SGD). We are able to prove linear convergence under weak strong convexity assumption. This requires no strong convexity assumption for minimizing the sum of smooth convex functions subject to a compact polyhedral set, which remains popular across machine learning community. Our PS2GD preserves the low-cost per iteration and high optimization accuracy via stochastic gradient variance-reduced technique, and admits a simple parallel implementation with mini-batches. Moreover, PS2GD is also applicable to dual problem of SVM with hinge loss. |
| Tasks | |
| Published | 2016-12-16 |
| URL | http://arxiv.org/abs/1612.05356v3 |
| http://arxiv.org/pdf/1612.05356v3.pdf | |
| PWC | https://paperswithcode.com/paper/projected-semi-stochastic-gradient-descent |
| Repo | |
| Framework | |
Accent Classification with Phonetic Vowel Representation
| Title | Accent Classification with Phonetic Vowel Representation |
| Authors | Zhenhao Ge, Yingyi Tan, Aravind Ganapathiraju |
| Abstract | Previous accent classification research focused mainly on detecting accents with pure acoustic information without recognizing accented speech. This work combines phonetic knowledge such as vowels with acoustic information to build Guassian Mixture Model (GMM) classifier with Perceptual Linear Predictive (PLP) features, optimized by Hetroscedastic Linear Discriminant Analysis (HLDA). With input about 20-second accented speech, this system achieves classification rate of 51% on a 7-way classification system focusing on the major types of accents in English, which is competitive to the state-of-the-art results in this field. |
| Tasks | |
| Published | 2016-02-24 |
| URL | http://arxiv.org/abs/1604.08095v1 |
| http://arxiv.org/pdf/1604.08095v1.pdf | |
| PWC | https://paperswithcode.com/paper/accent-classification-with-phonetic-vowel |
| Repo | |
| Framework | |
Towards reducing the multidimensionality of OLAP cubes using the Evolutionary Algorithms and Factor Analysis Methods
| Title | Towards reducing the multidimensionality of OLAP cubes using the Evolutionary Algorithms and Factor Analysis Methods |
| Authors | Sami Naouali, Semeh Ben Salem |
| Abstract | Data Warehouses are structures with large amount of data collected from heterogeneous sources to be used in a decision support system. Data Warehouses analysis identifies hidden patterns initially unexpected which analysis requires great memory and computation cost. Data reduction methods were proposed to make this analysis easier. In this paper, we present a hybrid approach based on Genetic Algorithms (GA) as Evolutionary Algorithms and the Multiple Correspondence Analysis (MCA) as Analysis Factor Methods to conduct this reduction. Our approach identifies reduced subset of dimensions from the initial subset p where p'<p where it is proposed to find the profile fact that is the closest to reference. GAs identify the possible subsets and the Khi formula of the ACM evaluates the quality of each subset. The study is based on a distance measurement between the reference and n facts profile extracted from the Warehouses. |
| Tasks | |
| Published | 2016-02-15 |
| URL | http://arxiv.org/abs/1602.04613v1 |
| http://arxiv.org/pdf/1602.04613v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-reducing-the-multidimensionality-of |
| Repo | |
| Framework | |
Crowd collectiveness measure via graph-based node clique learning
| Title | Crowd collectiveness measure via graph-based node clique learning |
| Authors | Weiya Ren |
| Abstract | Collectiveness motions of crowd systems have attracted a great deal of attentions in recently years. In this paper, we try to measure the collectiveness of a crowd system by the proposed node clique learning method. The proposed method is a graph based method, and investigates the influence from one node to other nodes. A node is represented by a set of nodes which named a clique, which is obtained by spreading information from this node to other nodes in graph. Then only nodes with sufficient information are selected as the clique of this node. The motion coherence between two nodes is defined by node cliques comparing. The collectiveness of a node and the collectiveness of the crowd system are defined by the nodes coherence. Self-driven particle (SDP) model and the crowd motion database are used to test the ability of the proposed method in measuring collectiveness. |
| Tasks | |
| Published | 2016-12-19 |
| URL | http://arxiv.org/abs/1612.06170v1 |
| http://arxiv.org/pdf/1612.06170v1.pdf | |
| PWC | https://paperswithcode.com/paper/crowd-collectiveness-measure-via-graph-based |
| Repo | |
| Framework | |
Learning Data Triage: Linear Decoding Works for Compressive MRI
| Title | Learning Data Triage: Linear Decoding Works for Compressive MRI |
| Authors | Yen-Huan Li, Volkan Cevher |
| Abstract | The standard approach to compressive sampling considers recovering an unknown deterministic signal with certain known structure, and designing the sub-sampling pattern and recovery algorithm based on the known structure. This approach requires looking for a good representation that reveals the signal structure, and solving a non-smooth convex minimization problem (e.g., basis pursuit). In this paper, another approach is considered: We learn a good sub-sampling pattern based on available training signals, without knowing the signal structure in advance, and reconstruct an accordingly sub-sampled signal by computationally much cheaper linear reconstruction. We provide a theoretical guarantee on the recovery error, and show via experiments on real-world MRI data the effectiveness of the proposed compressive MRI scheme. |
| Tasks | |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00734v1 |
| http://arxiv.org/pdf/1602.00734v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-data-triage-linear-decoding-works |
| Repo | |
| Framework | |
X-ray image separation via coupled dictionary learning
| Title | X-ray image separation via coupled dictionary learning |
| Authors | Nikos Deligiannis, João F. C. Mota, Bruno Cornelis, Miguel R. D. Rodrigues, Ingrid Daubechies |
| Abstract | In support of art investigation, we propose a new source sepa- ration method that unmixes a single X-ray scan acquired from double-sided paintings. Unlike prior source separation meth- ods, which are based on statistical or structural incoherence of the sources, we use visual images taken from the front- and back-side of the panel to drive the separation process. The coupling of the two imaging modalities is achieved via a new multi-scale dictionary learning method. Experimental results demonstrate that our method succeeds in the discrimination of the sources, while state-of-the-art methods fail to do so. |
| Tasks | Dictionary Learning |
| Published | 2016-05-20 |
| URL | http://arxiv.org/abs/1605.06474v1 |
| http://arxiv.org/pdf/1605.06474v1.pdf | |
| PWC | https://paperswithcode.com/paper/x-ray-image-separation-via-coupled-dictionary |
| Repo | |
| Framework | |
Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
| Title | Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks |
| Authors | Aliaksei Severyn, Alessandro Moschitti |
| Abstract | In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members of the pair. The matches are encoded as embeddings with additional parameters (dimensions), which are tuned by the network. These allows for better capturing interactions between questions and answers, resulting in a significant boost in accuracy. We test our models on two widely used answer sentence selection benchmarks. The results clearly show the effectiveness of our relational information, which allows our relatively simple network to approach the state of the art. |
| Tasks | |
| Published | 2016-04-05 |
| URL | http://arxiv.org/abs/1604.01178v1 |
| http://arxiv.org/pdf/1604.01178v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-relational-information-in-question |
| Repo | |
| Framework | |
By-passing the Kohn-Sham equations with machine learning
| Title | By-passing the Kohn-Sham equations with machine learning |
| Authors | Felix Brockherde, Leslie Vogt, Li Li, Mark E. Tuckerman, Kieron Burke, Klaus-Robert Müller |
| Abstract | Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields, ranging from materials science to biochemistry to astrophysics. Machine learning holds the promise of learning the kinetic energy functional via examples, by-passing the need to solve the Kohn-Sham equations. This should yield substantial savings in computer time, allowing either larger systems or longer time-scales to be tackled, but attempts to machine-learn this functional have been limited by the need to find its derivative. The present work overcomes this difficulty by directly learning the density-potential and energy-density maps for test systems and various molecules. Both improved accuracy and lower computational cost with this method are demonstrated by reproducing DFT energies for a range of molecular geometries generated during molecular dynamics simulations. Moreover, the methodology could be applied directly to quantum chemical calculations, allowing construction of density functionals of quantum-chemical accuracy. |
| Tasks | |
| Published | 2016-09-09 |
| URL | http://arxiv.org/abs/1609.02815v3 |
| http://arxiv.org/pdf/1609.02815v3.pdf | |
| PWC | https://paperswithcode.com/paper/by-passing-the-kohn-sham-equations-with |
| Repo | |
| Framework | |
Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods
| Title | Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods |
| Authors | Antoine Gautier, Quynh Nguyen, Matthias Hein |
| Abstract | The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show under quite weak assumptions on the data that a particular class of feedforward neural networks can be trained globally optimal with a linear convergence rate with our nonlinear spectral method. Up to our knowledge this is the first practically feasible method which achieves such a guarantee. While the method can in principle be applied to deep networks, we restrict ourselves for simplicity in this paper to one and two hidden layer networks. Our experiments confirm that these models are rich enough to achieve good performance on a series of real-world datasets. |
| Tasks | |
| Published | 2016-10-28 |
| URL | http://arxiv.org/abs/1610.09300v1 |
| http://arxiv.org/pdf/1610.09300v1.pdf | |
| PWC | https://paperswithcode.com/paper/globally-optimal-training-of-generalized |
| Repo | |
| Framework | |
Dominant Codewords Selection with Topic Model for Action Recognition
| Title | Dominant Codewords Selection with Topic Model for Action Recognition |
| Authors | Hirokatsu Kataoka, Masaki Hayashi, Kenji Iwata, Yutaka Satoh, Yoshimitsu Aoki, Slobodan Ilic |
| Abstract | In this paper, we propose a framework for recognizing human activities that uses only in-topic dominant codewords and a mixture of intertopic vectors. Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities. In LDA topic modeling, action videos (documents) are represented by a bag-of-words (input from a dictionary), and these are based on improved dense trajectories. The output topics correspond to human motion primitives, such as finger moving or subtle leg motion. We eliminate the impurities, such as missed tracking or changing light conditions, in each motion primitive. The assembled vector of motion primitives is an improved representation of the action. We demonstrate our method on four different datasets. |
| Tasks | Temporal Action Localization |
| Published | 2016-05-01 |
| URL | http://arxiv.org/abs/1605.00324v1 |
| http://arxiv.org/pdf/1605.00324v1.pdf | |
| PWC | https://paperswithcode.com/paper/dominant-codewords-selection-with-topic-model |
| Repo | |
| Framework | |
Comparison of the COG Defuzzification Technique and Its Variations to the GPA Index
| Title | Comparison of the COG Defuzzification Technique and Its Variations to the GPA Index |
| Authors | Michael Gr. Voskoglou |
| Abstract | The Center of Gravity (COG) method is one of the most popular defuzzification techniques of fuzzy mathematics. In earlier works the COG technique was properly adapted to be used as an assessment model (RFAM)and several variations of it (GRFAM, TFAM and TpFAM)were also constructed for the same purpose. In this paper the outcomes of all these models are compared to the corresponding outcomes of a traditional assessment method of the bi-valued logic, the Grade Point Average (GPA) Index. Examples are also presented illustrating our results. |
| Tasks | |
| Published | 2016-11-30 |
| URL | http://arxiv.org/abs/1612.00742v1 |
| http://arxiv.org/pdf/1612.00742v1.pdf | |
| PWC | https://paperswithcode.com/paper/comparison-of-the-cog-defuzzification |
| Repo | |
| Framework | |
Optimal Route Planning with Prioritized Task Scheduling for AUV Missions
| Title | Optimal Route Planning with Prioritized Task Scheduling for AUV Missions |
| Authors | S. Mahmoud Zadeh, D. Powers, K. Sammut, A. Lammas, A. M. Yazdani |
| Abstract | This paper presents a solution to Autonomous Underwater Vehicles (AUVs) large scale route planning and task assignment joint problem. Given a set of constraints (e.g., time) and a set of task priority values, the goal is to find the optimal route for underwater mission that maximizes the sum of the priorities and minimizes the total risk percentage while meeting the given constraints. Making use of the heuristic nature of genetic and swarm intelligence algorithms in solving NP-hard graph problems, Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) are employed to find the optimum solution, where each individual in the population is a candidate solution (route). To evaluate the robustness of the proposed methods, the performance of the all PS and GA algorithms are examined and compared for a number of Monte Carlo runs. Simulation results suggest that the routes generated by both algorithms are feasible and reliable enough, and applicable for underwater motion planning. However, the GA-based route planner produces superior results comparing to the results obtained from the PSO based route planner. |
| Tasks | Motion Planning |
| Published | 2016-04-12 |
| URL | http://arxiv.org/abs/1604.03303v1 |
| http://arxiv.org/pdf/1604.03303v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-route-planning-with-prioritized-task |
| Repo | |
| Framework | |
ParMAC: distributed optimisation of nested functions, with application to learning binary autoencoders
| Title | ParMAC: distributed optimisation of nested functions, with application to learning binary autoencoders |
| Authors | Miguel Á. Carreira-Perpiñán, Mehdi Alizadeh |
| Abstract | Many powerful machine learning models are based on the composition of multiple processing layers, such as deep nets, which gives rise to nonconvex objective functions. A general, recent approach to optimise such “nested” functions is the method of auxiliary coordinates (MAC). MAC introduces an auxiliary coordinate for each data point in order to decouple the nested model into independent submodels. This decomposes the optimisation into steps that alternate between training single layers and updating the coordinates. It has the advantage that it reuses existing single-layer algorithms, introduces parallelism, and does not need to use chain-rule gradients, so it works with nondifferentiable layers. With large-scale problems, or when distributing the computation is necessary for faster training, the dataset may not fit in a single machine. It is then essential to limit the amount of communication between machines so it does not obliterate the benefit of parallelism. We describe a general way to achieve this, ParMAC. ParMAC works on a cluster of processing machines with a circular topology and alternates two steps until convergence: one step trains the submodels in parallel using stochastic updates, and the other trains the coordinates in parallel. Only submodel parameters, no data or coordinates, are ever communicated between machines. ParMAC exhibits high parallelism, low communication overhead, and facilitates data shuffling, load balancing, fault tolerance and streaming data processing. We study the convergence of ParMAC and propose a theoretical model of its runtime and parallel speedup. We develop ParMAC to learn binary autoencoders for fast, approximate image retrieval. We implement it in MPI in a distributed system and demonstrate nearly perfect speedups in a 128-processor cluster with a training set of 100 million high-dimensional points. |
| Tasks | Image Retrieval |
| Published | 2016-05-30 |
| URL | http://arxiv.org/abs/1605.09114v1 |
| http://arxiv.org/pdf/1605.09114v1.pdf | |
| PWC | https://paperswithcode.com/paper/parmac-distributed-optimisation-of-nested |
| Repo | |
| Framework | |
Low-Rank Dynamic Mode Decomposition: Optimal Solution in Polynomial-Time
| Title | Low-Rank Dynamic Mode Decomposition: Optimal Solution in Polynomial-Time |
| Authors | Patrick Héas, Cédric Herzet |
| Abstract | This work studies the linear approximation of high-dimensional dynamical systems using low-rank dynamic mode decomposition (DMD). Searching this approximation in a data-driven approach is formalised as attempting to solve a low-rank constrained optimisation problem. This problem is non-convex and state-of-the-art algorithms are all sub-optimal. This paper shows that there exists a closed-form solution, which is computed in polynomial time, and characterises the l2-norm of the optimal approximation error. The paper also proposes low-complexity algorithms building reduced models from this optimal solution, based on singular value decomposition or eigen value decomposition. The algorithms are evaluated by numerical simulations using synthetic and physical data benchmarks. |
| Tasks | |
| Published | 2016-10-10 |
| URL | https://arxiv.org/abs/1610.02962v7 |
| https://arxiv.org/pdf/1610.02962v7.pdf | |
| PWC | https://paperswithcode.com/paper/low-rank-dynamic-mode-decomposition-optimal |
| Repo | |
| Framework | |
Automatic Generation of Probabilistic Programming from Time Series Data
| Title | Automatic Generation of Probabilistic Programming from Time Series Data |
| Authors | Anh Tong, Jaesik Choi |
| Abstract | Probabilistic programming languages represent complex data with intermingled models in a few lines of code. Efficient inference algorithms in probabilistic programming languages make possible to build unified frameworks to compute interesting probabilities of various large, real-world problems. When the structure of model is given, constructing a probabilistic program is rather straightforward. Thus, main focus have been to learn the best model parameters and compute marginal probabilities. In this paper, we provide a new perspective to build expressive probabilistic program from continue time series data when the structure of model is not given. The intuition behind of our method is to find a descriptive covariance structure of time series data in nonparametric Gaussian process regression. We report that such descriptive covariance structure efficiently derives a probabilistic programming description accurately. |
| Tasks | Probabilistic Programming, Time Series |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.00710v2 |
| http://arxiv.org/pdf/1607.00710v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-generation-of-probabilistic |
| Repo | |
| Framework | |
