Scalable sequential alternating proximal methods for sparse structural SVMs and CRFs

Structural Support Vector Machines (SSVMs) and Conditional Random Fields (CRFs) are popular discriminative methods used for classifying structured and complex objects like parse trees, image segments and part-of-speech tags. The datasets involved are very large dimensional, and the models designed using typical training algorithms for SSVMs and CRFs are non-sparse. This non-sparse nature of models results in slow inference. Thus, there is a need to devise new algorithms for sparse SSVM and CRF classifier design. Use of elastic net and L1-regularizer has already been explored for solving primal CRF and SSVM problems, respectively, to design sparse classifiers. In this work, we focus on dual elastic net regularized SSVM and CRF. By exploiting the weakly coupled structure of these convex programming problems, we propose a new sequential alternating proximal (SAP) algorithm to solve these dual problems. This algorithm works by sequentially visiting each training set example and solving a simple subproblem restricted to a small subset of variables associated with that example. Numerical experiments on various benchmark sequence labeling datasets demonstrate that the proposed algorithm scales well. Further, the classifiers designed are sparser than those designed by solving the respective primal problems and demonstrate comparable generalization performance. Thus, the proposed SAP algorithm is a useful alternative for sparse SSVM and CRF classifier design.

Climate change scenarios of surface solar radiation in data sparse regions: a case study in Malaprabha River Basin, India

A variety of methods are available to estimate future solar radiation (SR) scenarios at spatial scales that are appropriate for local climate change impact assessment. However, there are no clear guidelines available in the literature to decide which methodologies are most suitable for different applications. Three methodologies to guide the estimation of SR are discussed in this study, namely: Case 1: SR is measured, Case 2: SR is measured but sparse and Case 3: SR is not measured. In Case 1, future SR scenarios are derived using several downscaling methodologies that transfer the simulated large-scale information of global climate models to a local scale ( measurements). In Case 2, the SR was first estimated at the local scale for a longer time period using sparse measured records, and then future scenarios were derived using several downscaling methodologies. In Case 3: the SR was first estimated at a regional scale for a longer time period using complete or sparse measured records of SR from which SR at the local scale was estimated. Finally, the future scenarios were derived using several downscaling methodologies. The lack of observed SR data, especially in developing countries, has hindered various climate change impact studies. Hence, this was further elaborated by applying the Case 3 methodology to a semi-arid Malaprabha reservoir catchment in southern India. A support vector machine was used in downscaling SR. Future monthly scenarios of SR were estimated from simulations of third-generation Canadian General Circulation Model (CGCM3) for various SRES emission scenarios (A1B, A2, B1, and COMMIT). Results indicated a projected decrease of 0.4 to 12.2 W m(-2) yr(-1) in SR during the period 2001-2100 across the 4 scenarios. SR was calculated using the modified Hargreaves method. The decreasing trends for the future were in agreement with the simulations of SR from the CGCM3 model directly obtained for the 4 scenarios.

Joint Approximately Sparse Channel Estimation and Data Detection in OFDM Systems Using Sparse Bayesian Learning

It is well known that the impulse response of a wide-band wireless channel is approximately sparse, in the sense that it has a small number of significant components relative to the channel delay spread. In this paper, we consider the estimation of the unknown channel coefficients and its support in OFDM systems using a sparse Bayesian learning (SBL) framework for exact inference. In a quasi-static, block-fading scenario, we employ the SBL algorithm for channel estimation and propose a joint SBL (J-SBL) and a low-complexity recursive J-SBL algorithm for joint channel estimation and data detection. In a time-varying scenario, we use a first-order autoregressive model for the wireless channel and propose a novel, recursive, low-complexity Kalman filtering-based SBL (KSBL) algorithm for channel estimation. We generalize the KSBL algorithm to obtain the recursive joint KSBL algorithm that performs joint channel estimation and data detection. Our algorithms can efficiently recover a group of approximately sparse vectors even when the measurement matrix is partially unknown due to the presence of unknown data symbols. Moreover, the algorithms can fully exploit the correlation structure in the multiple measurements. Monte Carlo simulations illustrate the efficacy of the proposed techniques in terms of the mean-square error and bit error rate performance.

Energy Efficient GPS Acquisition with Sparse-GPS

Following rising demands in positioning with GPS, low-cost receivers are becoming widely available; but their energy demands are still too high. For energy efficient GPS sensing in delay-tolerant applications, the possibility of offloading a few milliseconds of raw signal samples and leveraging the greater processing power of the cloud for obtaining a position fix is being actively investigated. In an attempt to reduce the energy cost of this data offloading operation, we propose Sparse-GPS(1): a new computing framework for GPS acquisition via sparse approximation. Within the framework, GPS signals can be efficiently compressed by random ensembles. The sparse acquisition information, pertaining to the visible satellites that are embedded within these limited measurements, can subsequently be recovered by our proposed representation dictionary. By extensive empirical evaluations, we demonstrate the acquisition quality and energy gains of Sparse-GPS. We show that it is twice as energy efficient than offloading uncompressed data, and has 5-10 times lower energy costs than standalone GPS; with a median positioning accuracy of 40 m.

NESTED SPARSE BAYESIAN LEARNING FOR BLOCK-SPARSE SIGNALS WITH INTRA-BLOCK CORRELATION

In this work, we address the recovery of block sparse vectors with intra-block correlation, i.e., the recovery of vectors in which the correlated nonzero entries are constrained to lie in a few clusters, from noisy underdetermined linear measurements. Among Bayesian sparse recovery techniques, the cluster Sparse Bayesian Learning (SBL) is an efficient tool for block-sparse vector recovery, with intra-block correlation. However, this technique uses a heuristic method to estimate the intra-block correlation. In this paper, we propose the Nested SBL (NSBL) algorithm, which we derive using a novel Bayesian formulation that facilitates the use of the monotonically convergent nested Expectation Maximization (EM) and a Kalman filtering based learning framework. Unlike the cluster-SBL algorithm, this formulation leads to closed-form EMupdates for estimating the correlation coefficient. We demonstrate the efficacy of the proposed NSBL algorithm using Monte Carlo simulations.

An iterative framework for sparse signal reconstruction algorithms

It has been shown that iterative re-weighted strategies will often improve the performance of many sparse reconstruction algorithms. However, these strategies are algorithm dependent and cannot be easily extended for an arbitrary sparse reconstruction algorithm. In this paper, we propose a general iterative framework and a novel algorithm which iteratively enhance the performance of any given arbitrary sparse reconstruction algorithm. We theoretically analyze the proposed method using restricted isometry property and derive sufficient conditions for convergence and performance improvement. We also evaluate the performance of the proposed method using numerical experiments with both synthetic and real-world data. (C) 2014 Elsevier B.V. All rights reserved.

Sparse Representation Based Acoustic Rangefinders: From Sensor Platforms to Mobile Devices

Acoustic rangerfinders are a promising technology for accurate proximity detection, a critical requirement for many emerging mobile computing applications. While state-of-the-art systems deliver robust ranging performance, the computational intensiveness of their detection mechanism expedites the energy depletion of the associated devices that are typically powered by batteries. The contribution of this article is fourfold. First, it outlines the common factors that are important for ranging. Second, it presents a review of acoustic rangers and identifies their potential problems. Third, it explores the design of an information processing framework based on sparse representation that could potentially address existing challenges, especially for mobile devices. Finally, it presents mu-BeepBeep: a low energy acoustic ranging service for mobile devices, and empirically evaluates its benefits.

Robust tracking with interest points: A sparse representation approach

Visual tracking is an important task in various computer vision applications including visual surveillance, human computer interaction, event detection, video indexing and retrieval. Recent state of the art sparse representation (SR) based trackers show better robustness than many of the other existing trackers. One of the issues with these SR trackers is low execution speed. The particle filter framework is one of the major aspects responsible for slow execution, and is common to most of the existing SR trackers. In this paper,(1) we propose a robust interest point based tracker in l(1) minimization framework that runs at real-time with performance comparable to the state of the art trackers. In the proposed tracker, the target dictionary is obtained from the patches around target interest points. Next, the interest points from the candidate window of the current frame are obtained. The correspondence between target and candidate points is obtained via solving the proposed l(1) minimization problem. In order to prune the noisy matches, a robust matching criterion is proposed, where only the reliable candidate points that mutually match with target and candidate dictionary elements are considered for tracking. The object is localized by measuring the displacement of these interest points. The reliable candidate patches are used for updating the target dictionary. The performance and accuracy of the proposed tracker is benchmarked with several complex video sequences. The tracker is found to be considerably fast as compared to the reported state of the art trackers. The proposed tracker is further evaluated for various local patch sizes, number of interest points and regularization parameters. The performance of the tracker for various challenges including illumination change, occlusion, and background clutter has been quantified with a benchmark dataset containing 50 videos. (C) 2014 Elsevier B.V. All rights reserved.

Sparse coding based VLAD for efficient image retrieval

Representing images and videos in the form of compact codes has emerged as an important research interest in the vision community, in the context of web scale image/video search. Recently proposed Vector of Locally Aggregated Descriptors (VLAD), has been shown to outperform the existing retrieval techniques, while giving a desired compact representation. VLAD aggregates the local features of an image in the feature space. In this paper, we propose to represent the local features extracted from an image, as sparse codes over an over-complete dictionary, which is obtained by K-SVD based dictionary training algorithm. The proposed VLAD aggregates the residuals in the space of these sparse codes, to obtain a compact representation for the image. Experiments are performed over the `Holidays' database using SIFT features. The performance of the proposed method is compared with the original VLAD. The 4% increment in the mean average precision (mAP) indicates the better retrieval performance of the proposed sparse coding based VLAD.

LDPC Code Designs Based on root I Matrices

LDPC codes can be constructed by tiling permutation matrices that belong to the square root of identity type and similar algebraic structures. We investigate into the properties of such codes. We also present code structures that are amenable for efficient encoding.

Modified Greedy Pursuits for Improving Sparse Recovery

Compressive Sensing (CS) theory combines the signal sampling and compression for sparse signals resulting in reduction in sampling rate. In recent years, many recovery algorithms have been proposed to reconstruct the signal efficiently. Subspace Pursuit and Compressive Sampling Matching Pursuit are some of the popular greedy methods. Also, Fusion of Algorithms for Compressed Sensing is a recently proposed method where several CS reconstruction algorithms participate and the final estimate of the underlying sparse signal is determined by fusing the estimates obtained from the participating algorithms. All these methods involve solving a least squares problem which may be ill-conditioned, especially in the low dimension measurement regime. In this paper, we propose a step prior to least squares to ensure the well-conditioning of the least squares problem. Using Monte Carlo simulations, we show that in low dimension measurement scenario, this modification improves the reconstruction capability of the algorithm in clean as well as noisy measurement cases.

Optimum Parameter Selection in Sparse Reconstruction of Frequency-Domain Optical-Coherence Tomography Signals

For a multilayered specimen, the back-scattered signal in frequency-domain optical-coherence tomography (FDOCT) is expressible as a sum of cosines, each corresponding to a change of refractive index in the specimen. Each of the cosines represent a peak in the reconstructed tomogram. We consider a truncated cosine series representation of the signal, with the constraint that the coefficients in the basis expansion be sparse. An l(2) (sum of squared errors) data error is considered with an l(1) (summation of absolute values) constraint on the coefficients. The optimization problem is solved using Weiszfeld's iteratively reweighted least squares (IRLS) algorithm. On real FDOCT data, improved results are obtained over the standard reconstruction technique with lower levels of background measurement noise and artifacts due to a strong l(1) penalty. The previous sparse tomogram reconstruction techniques in the literature proposed collecting sparse samples, necessitating a change in the data capturing process conventionally used in FDOCT. The IRLS-based method proposed in this paper does not suffer from this drawback.

A Split-and-Merge Dictionary Learning Algorithm for Sparse Representation: Application to Image Denoising

In big data image/video analytics, we encounter the problem of learning an over-complete dictionary for sparse representation from a large training dataset, which cannot be processed at once because of storage and computational constraints. To tackle the problem of dictionary learning in such scenarios, we propose an algorithm that exploits the inherent clustered structure of the training data and make use of a divide-and-conquer approach. The fundamental idea behind the algorithm is to partition the training dataset into smaller clusters, and learn local dictionaries for each cluster. Subsequently, the local dictionaries are merged to form a global dictionary. Merging is done by solving another dictionary learning problem on the atoms of the locally trained dictionaries. This algorithm is referred to as the split-and-merge algorithm. We show that the proposed algorithm is efficient in its usage of memory and computational complexity, and performs on par with the standard learning strategy, which operates on the entire data at a time. As an application, we consider the problem of image denoising. We present a comparative analysis of our algorithm with the standard learning techniques that use the entire database at a time, in terms of training and denoising performance. We observe that the split-and-merge algorithm results in a remarkable reduction of training time, without significantly affecting the denoising performance.

Joint Channel Estimation and Data Detection in MIMO-OFDM Systems: A Sparse Bayesian Learning Approach

The impulse response of wireless channels between the N-t transmit and N-r receive antennas of a MIMO-OFDM system are group approximately sparse (ga-sparse), i.e., NtNt the channels have a small number of significant paths relative to the channel delay spread and the time-lags of the significant paths between transmit and receive antenna pairs coincide. Often, wireless channels are also group approximately cluster-sparse (gac-sparse), i.e., every ga-sparse channel consists of clusters, where a few clusters have all strong components while most clusters have all weak components. In this paper, we cast the problem of estimating the ga-sparse and gac-sparse block-fading and time-varying channels in the sparse Bayesian learning (SBL) framework and propose a bouquet of novel algorithms for pilot-based channel estimation, and joint channel estimation and data detection, in MIMO-OFDM systems. The proposed algorithms are capable of estimating the sparse wireless channels even when the measurement matrix is only partially known. Further, we employ a first-order autoregressive modeling of the temporal variation of the ga-sparse and gac-sparse channels and propose a recursive Kalman filtering and smoothing (KFS) technique for joint channel estimation, tracking, and data detection. We also propose novel, parallel-implementation based, low-complexity techniques for estimating gac-sparse channels. Monte Carlo simulations illustrate the benefit of exploiting the gac-sparse structure in the wireless channel in terms of the mean square error (MSE) and coded bit error rate (BER) performance.

Similarity of Matrices Over Local Rings of Length Two

Let R be a (commutative) local principal ideal ring of length two, for example, the ring R = Z/p(2)Z with p prime. In this paper, we develop a theory of normal forms for similarity classes in the matrix rings M-n (R) by interpreting them in terms of extensions of R t]-modules. Using this theory, we describe the similarity classes in M-n (R) for n <= 4, along with their centralizers. Among these, we characterize those classes which are similar to their transposes. Non-self-transpose classes are shown to exist for all n > 3. When R has finite residue field of order q, we enumerate the similarity classes and the cardinalities of their centralizers as polynomials in q. Surprisingly, the polynomials representing the number of similarity classes in M-n (R) turn out to have non-negative integer coefficients.