First, we introduce a splitting algorithm to minimize a sum of three convex functions. The algorithm is of primal dual kind and is inspired by recent results of Vu and Condat. Second, we provide a randomized version o...
详细信息
ISBN:
(纸本)9781479936946
First, we introduce a splitting algorithm to minimize a sum of three convex functions. The algorithm is of primal dual kind and is inspired by recent results of Vu and Condat. Second, we provide a randomized version of the algorithm based on the idea of coordinate descent. Finally, we address two applications of our method: (i) for stochastic minibatch optimization;and (ii) for distributed optimization.
In this paper, we propose a dictionary updating method and show numerically that it can converge to a dictionary that outperforms the dictionary derived by the K-SVD method. The proposed method is based on the proxima...
详细信息
ISBN:
(纸本)9781479911806
In this paper, we propose a dictionary updating method and show numerically that it can converge to a dictionary that outperforms the dictionary derived by the K-SVD method. The proposed method is based on the proximal point approach used in the convex optimization algorithm. We incorporate the approach into the well-known MOD and combine the result with the K-SVD method to obtain the proposed method. We analyze the complexity of the proposed method and compare it with that of the K-SVD method. The results of experiments demonstrate that our method outperforms K-SVD with only a slight increase in the execution time.
We introduce a new method for estimating the regime-switching stochastic volatility models from the historical prices. Our methodology is based on a novel version of the assumed density filter (ADF). We estimate the s...
详细信息
ISBN:
(纸本)9781509007462
We introduce a new method for estimating the regime-switching stochastic volatility models from the historical prices. Our methodology is based on a novel version of the assumed density filter (ADF). We estimate the switching model by maximizing the quasi-likelihood function of our ADF. The simulation experiments show the efficiency of our method. Then we analyze different market price histories for consistency with a regime-shifting model.
There arises the need in many wireless network applications to infer and track different models of interest. Some nodes in the network are informed, where they observe the different models and send information to the ...
详细信息
ISBN:
(纸本)9781509007462
There arises the need in many wireless network applications to infer and track different models of interest. Some nodes in the network are informed, where they observe the different models and send information to the uninformed ones. Each uninformed node responds to one informed node and joins its group. In this work, we suggest an adaptive and distributed clustering and partitioning approach that allows the informed nodes in the network to be clustered into many groups according to the observed models;then we apply a decentralized strategy to part the uninformed nodes into groups of approximately equal size around the informed nodes.
Classical supervised learning via empirical risk (or negative log-likelihood) minimization hinges upon the assumption that the testing distribution coincides with the training distribution. This assumption can be chal...
详细信息
ISBN:
(纸本)9781728166629
Classical supervised learning via empirical risk (or negative log-likelihood) minimization hinges upon the assumption that the testing distribution coincides with the training distribution. This assumption can be challenged in modern applications of machinelearning in which learningmachines may operate at prediction time with testing data whose distribution departs from the one of the training data. We revisit the superquantile regression method by proposing a first-order optimization algorithm to minimize a superquantile-based learning objective. The proposed algorithm is based on smoothing the superquantile function by infimal convolution. Promising numerical results illustrate the interest of the approach towards safer supervised learning.
This work deals with the elimination of sensitivity to sensor orientation in the task of human daily activity recognition using a single miniature inertial sensor. The proposed method detects time intervals of walking...
详细信息
ISBN:
(纸本)9781467310260
This work deals with the elimination of sensitivity to sensor orientation in the task of human daily activity recognition using a single miniature inertial sensor. The proposed method detects time intervals of walking, automatically estimating the orientation in these intervals and transforming the observed signals to a "virtual" sensor orientation. Classification results show that excellent performance, in terms of both precision and recall (up to 100%), is achieved, for long-term recordings in real-life settings.
Multivariate signalprocessing is often based on dimensionality reduction techniques. We propose a new method, Dynamical Component Analysis (DyCA), leading to a classification of the underlying dynamics and - for a ce...
详细信息
ISBN:
(纸本)9781538654774
Multivariate signalprocessing is often based on dimensionality reduction techniques. We propose a new method, Dynamical Component Analysis (DyCA), leading to a classification of the underlying dynamics and - for a certain type of dynamics - to a signal subspace representing the dynamics of the data. In this paper the algorithm is derived leading to a generalized eigenvalue problem of correlation matrices. The application of the DyCA on high-dimensional chaotic signals is presented both for simulated data as well as real EEG data of epileptic seizures.
Multi-view learning is a classification setting in which feature vectors consist of multiple views. The goal in this setting is to find a classifier for some or all of the views. We consider a limiting case of multi-v...
详细信息
ISBN:
(纸本)9781479936946
Multi-view learning is a classification setting in which feature vectors consist of multiple views. The goal in this setting is to find a classifier for some or all of the views. We consider a limiting case of multi-view learning termed surrogate supervision multi-view learning (SSML). In the SSML setting, training data consists of two types: unlabeled two-view data examples and labeled single view examples. The goal in this setting is to find a classifier for the view for which no labels are available. In this paper, we analyze the case in which the data is Gaussian distributed and the classifiers on each view are linear. For this setting, we provide a theoretical analysis for the performance mismatch between the error associated with a classifier trained in the SSML setting and a classifier trained in the direct supervision setting.
In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining t...
详细信息
ISBN:
(纸本)0780395174
In this paper, a new method is introduced to speed up the recursive feature ranking procedure by using the margin distribution of a trained SVM. The method, M-RFE, continuously eliminates features without retraining the SVM as long as the margin distribution of the SVM does not change significantly. Synthetic datasets and two benchmark microarray datasets were tested on M-RFE. Comparison with original SVM-RFE shows that our method speeds up the feature ranking procedure considerably with little or no performance degradation. Comparison of M-RFE to a similar speed up technique, E-RFE, provides similar classification performance, but with reduced complexity.
This paper presents the application of the kernel signal to noise ratio (KSNR) in the context of feature extraction to general machinelearning and signalprocessing domains. The proposed approach maximizes the signal...
详细信息
ISBN:
(纸本)9781467310260
This paper presents the application of the kernel signal to noise ratio (KSNR) in the context of feature extraction to general machinelearning and signalprocessing domains. The proposed approach maximizes the signal variance while minimizes the estimated noise variance in a reproducing kernel Hilbert space (RKHS). The KSNR can be used in any kernel method to deal with correlated (possibly non-Gaussian) noise. We illustrate the method in nonlinear regression examples, dependence estimation and causal inference, nonlinear channel equalization, and nonlinear feature extraction from high-dimensional satellite images. Results show that the proposed KSNR yields more fitted solutions and extracts more noise-free features when confronted with standard approaches.
暂无评论