Sparsity inducing regularization is an important part for learning over-complete visual representations. Despite the popularity of $\ell_1$ regularization, in this paper, we investigate the usage of non-convex regularizations in this problem. Our contribution consists of three parts. First, we propose the leaky capped norm regularization (LCNR), which allows model weights below a certain threshold to be regularized more strongly as opposed to those above, therefore imposes strong sparsity and only introduces controllable estimation bias. We propose a majorization-minimization algorithm to optimize the joint objective function. Second, our study over monocular 3D shape recovery and neural networks with LCNR outperforms $\ell_1$ and other non-convex regularizations, achieving state-of-the-art performance and faster convergence. Third, we prove a theoretical global convergence speed on the 3D recovery problem. To the best of our knowledge, this is the first convergence analysis of the 3D recovery problem.

We propose a rank-$k$ variant of the classical Frank-Wolfe algorithm to solve convex optimization over a trace-norm ball. Our algorithm replaces the top singular-vector computation ($1$-SVD) in Frank-Wolfe with a top-$k$ singular-vector computation ($k$-SVD), which can be done by repeatedly applying $1$-SVD $k$ times. Alternatively, our algorithm can be viewed as a rank-$k$ restricted version of projected gradient descent. We show that our algorithm has a linear convergence rate when the objective function is smooth and strongly convex, and the optimal solution has rank at most $k$. This improves the convergence rate and the total time complexity of the Frank-Wolfe method and its variants.

This work brings together two powerful concepts in Gaussian processes: the variational approach to sparse approximation and the spectral representation of Gaussian processes. This gives rise to an approximation that inherits the benefits of the variational approach but with the representational power and computational scalability of spectral representations. The work hinges on a key result that there exist spectral features related to a finite domain of the Gaussian process which exhibit almost-independent covariances. We derive these expressions for Matern kernels in one dimension, and generalize to more dimensions using kernels with specific structures. Under the assumption of additive Gaussian noise, our method requires only a single pass through the dataset, making for very fast and accurate computation. We fit a model to 4 million training points in just a few minutes on a standard laptop. With non-conjugate likelihoods, our MCMC scheme reduces the cost of computation from O(NM2) (for a sparse Gaussian process) to O(NM) per iteration, where N is the number of data and M is the number of features.

This study presents an efficient incremental/decremental approach for big streams based on Kernel Ridge Regression (KRR), a frequently used data analysis in cloud centers. To avoid reanalyzing the whole dataset whenever sensors receive new training data, typical incremental KRR used a single-instance mechanism for updating an existing system. However, this inevitably increased redundant computational time, not to mention applicability to big streams. To this end, the proposed mechanism supports incremental/decremental processing for both single and multiple samples (i.e., batch processing). A large scale of data can be divided into batches, processed by a machine, without sacrificing the accuracy. Moreover, incremental/decremental analyses in empirical and intrinsic space are also proposed in this study to handle different types of data either with a large number of samples or high feature dimensions, whereas typical methods focused only on one type. At the end of this study, we further the proposed mechanism to statistical Kernelized Bayesian Regression, so that uncertainty modeling with incremental/decremental computation becomes applicable. Experimental results showed that computational time was significantly reduced, better than the original nonincremental design and the typical single incremental method. Furthermore, the accuracy of the proposed method remained the same as the baselines. This implied that the system enhanced efficiency without sacrificing the accuracy. These findings proved that the proposed method was appropriate for variable streaming data analysis, thereby demonstrating the effectiveness of the proposed method.

To ensure interpretability of extracted sources in tensor decomposition, we introduce in this paper a dictionarybased tensor canonical polyadic decomposition which enforces one factor to belong exactly to a known dictionary. A new formulation of sparse coding is proposed which enables high dimensional tensors dictionary-based canonical polyadic decomposition. The benefits of using a dictionary in tensor decomposition models are explored both in terms of parameter identifiability and estimation accuracy. Performances of the proposed algorithms are evaluated on the decomposition of simulated data and the unmixing of hyperspectral images. Index Terms tensor, multiway analysis, sparse coding, constrained optimization, spectral unmixing.

Near-future electric distribution grids operation will have to rely on demand-side flexibility, both by implementation of demand response strategies and by taking advantage of the intelligent management of increasingly common small-scale energy storage. The Home energy management system (HEMS), installed at low voltage residential clients, will play a crucial role on the flexibility provision to both system operators and market players like aggregators. Modeling and forecasting multi-period flexibility from residential prosumers, such as battery storage and electric water heater, while complying with internal constraints (comfort levels, data privacy) and uncertainty is a complex task. This papers describes a computational method that is capable of efficiently learn and define the feasibility flexibility space from controllable resources connected to a HEMS. An Evolutionary Particle Swarm Optimization (EPSO) algorithm is adopted and reshaped to derive a set of feasible temporal trajectories for the residential net-load, considering storage, flexible appliances, and predefined costumer preferences, as well as load and photovoltaic (PV) forecast uncertainty. A support vector data description (SVDD) algorithm is used to build models capable of classifying feasible and non-feasible HEMS operating trajectories upon request from an optimization/control algorithm operated by a DSO or market player.

The Information Bottleneck (IB) is a conceptual method for extracting the most compact, yet informative, representation of a set of variables, with respect to the target. It generalizes the notion of minimal sufficient statistics from classical parametric statistics to a broader information-theoretic sense. The IB curve defines the optimal trade-off between representation complexity and its predictive power. Specifically, it is achieved by minimizing the level of mutual information (MI) between the representation and the original variables, subject to a minimal level of MI between the representation and the target. This problem is shown to be in general NP hard. One important exception is the multivariate Gaussian case, for which the Gaussian IB (GIB) is known to obtain an analytical closed form solution, similar to Canonical Correlation Analysis (CCA). In this work we introduce a Gaussian lower bound to the IB curve; we find an embedding of the data which maximizes its "Gaussian part", on which we apply the GIB. This embedding provides an efficient (and practical) representation of any arbitrary data-set (in the IB sense), which in addition holds the favorable properties of a Gaussian distribution. Importantly, we show that the optimal Gaussian embedding is bounded from above by non-linear CCA. This allows a fundamental limit for our ability to Gaussianize arbitrary data-sets and solve complex problems by linear methods.

Canonical correlation analysis is a family of multivariate statistical methods for the analysis of paired sets of variables. Since its proposition, canonical correlation analysis has for instance been extended to extract relations between two sets of variables when the sample size is insufficient in relation to the data dimensionality, when the relations have been considered to be non-linear, and when the dimensionality is too large for human interpretation. This tutorial explains the theory of canonical correlation analysis including its regularised, kernel, and sparse variants. Additionally, the deep and Bayesian CCA extensions are briefly reviewed. Together with the numerical examples, this overview provides a coherent compendium on the applicability of the variants of canonical correlation analysis. By bringing together techniques for solving the optimisation problems, evaluating the statistical significance and generalisability of the canonical correlation model, and interpreting the relations, we hope that this article can serve as a hands-on tool for applying canonical correlation methods in data analysis.

The importance of interpretability of machine learning models has been increasing due to emerging enterprise predictive analytics, threat of data privacy, accountability of artificial intelligence in society, and so on. Piecewise linear models have been actively studied to achieve both accuracy and interpretability. They often produce competitive accuracy against state-of-the-art non-linear methods. In addition, their representations (i.e., rule-based segmentation plus sparse linear formula) are often preferred by domain experts. A disadvantage of such models, however, is high computational cost for simultaneous determinations of the number of "pieces" and cardinality of each linear predictor, which has restricted their applicability to middle-scale data sets. This paper proposes a distributed factorized asymptotic Bayesian (FAB) inference of learning piece-wise sparse linear models on distributed memory architectures. The distributed FAB inference solves the simultaneous model selection issue without communicating $O(N)$ data where N is the number of training samples and achieves linear scale-out against the number of CPU cores. Experimental results demonstrate that the distributed FAB inference achieves high prediction accuracy and performance scalability with both synthetic and benchmark data.

This paper proposes and studies a detection technique for adversarial scenarios (dubbed deterministic detection). This technique provides an alternative detection methodology in case the usual stochastic methods are not applicable: this can be because the studied phenomenon does not follow a stochastic sampling scheme, samples are high-dimensional and subsequent multiple-testing corrections render results overly conservative, sample sizes are too low for asymptotic results (as e.g. the central limit theorem) to kick in, or one cannot allow for the small probability of failure inherent to stochastic approaches. This paper instead designs a method based on insights from machine learning and online learning theory: this detection algorithm - named Online FAult Detection (FADO) - comes with theoretical guarantees of its detection capabilities. A version of the margin is found to regulate the detection performance of FADO. A precise expression is derived for bounding the performance, and experimental results are presented assessing the influence of involved quantities. A case study of scene detection is used to illustrate the approach. The technology is closely related to the linear perceptron rule, inherits its computational attractiveness and flexibility towards various extensions.