In this work we introduce a novel approach, based on sampling, for finding assignments that are likely to be solutions to stochastic constraint satisfaction problems and constraint optimisation problems. Our approach reduces the size of the original problem being analysed; by solving this reduced problem, with a given confidence probability, we obtain assignments that satisfy the chance constraints in the original model within prescribed error tolerance thresholds. To achieve this, we blend concepts from stochastic constraint programming and statistics. We discuss both exact and approximate variants of our method. The framework we introduce can be immediately employed in concert with existing approaches for solving stochastic constraint programs. A thorough computational study on a number of stochastic combinatorial optimisation problems demonstrates the effectiveness of our approach.

This paper discusses the effect of hubness in zero-shot learning, when ridge regression is used to find a mapping between the example space to the label space. Contrary to the existing approach, which attempts to find a mapping from the example space to the label space, we show that mapping labels into the example space is desirable to suppress the emergence of hubs in the subsequent nearest neighbor search step. Assuming a simple data model, we prove that the proposed approach indeed reduces hubness. This was verified empirically on the tasks of bilingual lexicon extraction and image labeling: hubness was reduced with both of these tasks and the accuracy was improved accordingly.

We introduce a very general method for sparse and large-scale variable selection. The large-scale regression settings is such that both the number of parameters and the number of samples are extremely large. The proposed method is based on careful combination of penalized estimators, each applied to a random projection of the sample space into a low-dimensional space. In one special case that we study in detail, the random projections are divided into non-overlapping blocks; each consisting of only a small portion of the original data. Within each block we select the projection yielding the smallest out-of-sample error. Our random ensemble estimator then aggregates the results according to new maximal-contrast voting scheme to determine the final selected set. Our theoretical results illuminate the effect on performance of increasing the number of non-overlapping blocks. Moreover, we demonstrate that statistical optimality is retained along with the computational speedup. The proposed method achieves minimax rates for approximate recovery over all estimators using the full set of samples. Furthermore, our theoretical results allow the number of subsamples to grow with the subsample size and do not require irrepresentable condition. The estimator is also compared empirically with several other popular high-dimensional estimators via an extensive simulation study, which reveals its excellent finite-sample performance.

We present a general regularization-based framework for Multi-task learning (MTL), in which the similarity between tasks can be learned or refined using $\ell_p$-norm Multiple Kernel learning (MKL). Based on this very general formulation (including a general loss function), we derive the corresponding dual formulation using Fenchel duality applied to Hermitian matrices. We show that numerous established MTL methods can be derived as special cases from both, the primal and dual of our formulation. Furthermore, we derive a modern dual-coordinate descend optimization strategy for the hinge-loss variant of our formulation and provide convergence bounds for our algorithm. As a special case, we implement in C++ a fast LibLinear-style solver for $\ell_p$-norm MKL. In the experimental section, we analyze various aspects of our algorithm such as predictive performance and ability to reconstruct task relationships on biologically inspired synthetic data, where we have full control over the underlying ground truth. We also experiment on a new dataset from the domain of computational biology that we collected for the purpose of this paper. It concerns the prediction of transcription start sites (TSS) over nine organisms, which is a crucial task in gene finding. Our solvers including all discussed special cases are made available as open-source software as part of the SHOGUN machine learning toolbox (available at \url{http://shogun.ml}).

The linking genotype to phenotype is the fundamental aim of modern genetics. We focus on study of links between gene expression data and phenotype data through integrative analysis. We propose three approaches. 1) The inherent complexity of phenotypes makes high-throughput phenotype profiling a very difficult and laborious process. We propose a method of automated multi-dimensional profiling which uses gene expression similarity. Large-scale analysis show that our method can provide robust profiling that reveals different phenotypic aspects of samples. This profiling technique is also capable of interpolation and extrapolation beyond the phenotype information given in training data. It can be used in many applications, including facilitating experimental design and detecting confounding factors. 2) Phenotype association analysis problems are complicated by small sample size and high dimensionality. Consequently, phenotype-associated gene subsets obtained from training data are very sensitive to selection of training samples, and the constructed sample phenotype classifiers tend to have poor generalization properties. To eliminate these obstacles, we propose a novel approach that generates sequences of increasingly discriminative gene cluster combinations. Our experiments on both simulated and real datasets show robust and accurate classification performance. 3) Many complex phenotypes, such as cancer, are the product of not only gene expression, but also gene interaction. We propose an integrative approach to find gene network modules that activate under different phenotype conditions. Using our method, we discovered cancer subtype-specific network modules, as well as the ways in which these modules coordinate. In particular, we detected a breast-cancer specific tumor suppressor network module with a hub gene, PDGFRL, which may play an important role in this module.

Finding statistically significant high-order interaction features in predictive modeling is important but challenging task. The difficulty lies in the fact that, for a recent applications with high-dimensional covariates, the number of possible high-order interaction features would be extremely large. Identifying statistically significant features from such a huge pool of candidates would be highly challenging both in computational and statistical senses. To work with this problem, we consider a two stage algorithm where we first select a set of high-order interaction features by marginal screening, and then make statistical inferences on the regression model fitted only with the selected features. Such statistical inferences are called post-selection inference (PSI), and receiving an increasing attention in the literature. One of the seminal recent advancements in PSI literature is the works by Lee et al. where the authors presented an algorithmic framework for computing exact sampling distributions in PSI. A main challenge when applying their approach to our high-order interaction models is to cope with the fact that PSI in general depends not only on the selected features but also on the unselected features, making it hard to apply to our extremely high-dimensional high-order interaction models. The goal of this paper is to overcome this difficulty by introducing a novel efficient method for PSI. Our key idea is to exploit the underlying tree structure among high-order interaction features, and to develop a pruning method of the tree which enables us to quickly identify a group of unselected features that are guaranteed to have no influence on PSI. The experimental results indicate that the proposed method allows us to reliably identify statistically significant high-order interaction features with reasonable computational cost.

Fairness-aware learning is a novel framework for classification tasks. Like regular empirical risk minimization (ERM), it aims to learn a classifier with a low error rate, and at the same time, for the predictions of the classifier to be independent of sensitive features, such as gender, religion, race, and ethnicity. Existing methods can achieve low dependencies on given samples, but this is not guaranteed on unseen samples. The existing fairness-aware learning algorithms employ different dependency measures, and each algorithm is specifically designed for a particular one. Such diversity makes it difficult to theoretically analyze and compare them. In this paper, we propose a general framework for fairness-aware learning that uses f-divergences and that covers most of the dependency measures employed in the existing methods. We introduce a way to estimate the f-divergences that allows us to give a unified analysis for the upper bound of the estimation error; this bound is tighter than that of the existing convergence rate analysis of the divergence estimation. With our divergence estimate, we propose a fairness-aware learning algorithm, and perform a theoretical analysis of its generalization error. Our analysis reveals that, under mild assumptions and even with enforcement of fairness, the generalization error of our method is $O(\sqrt{1/n})$, which is the same as that of the regular ERM. In addition, and more importantly, we show that, for any f-divergence, the upper bound of the estimation error of the divergence is $O(\sqrt{1/n})$. This indicates that our fairness-aware learning algorithm guarantees low dependencies on unseen samples for any dependency measure represented by an f-divergence.

Spectral clustering is a technique that clusters elements using the top few eigenvectors of their (possibly normalized) similarity matrix. The quality of spectral clustering is closely tied to the convergence properties of these principal eigenvectors. This rate of convergence has been shown to be identical for both the normalized and unnormalized variants in recent random matrix theory literature. However, normalization for spectral clustering is commonly believed to be beneficial [Stat. Comput. 17 (2007) 395-416]. Indeed, our experiments show that normalization improves prediction accuracy. In this paper, for the popular stochastic blockmodel, we theoretically show that normalization shrinks the spread of points in a class by a constant fraction under a broad parameter regime. As a byproduct of our work, we also obtain sharp deviation bounds of empirical principal eigenvalues of graphs generated from a stochastic blockmodel.

Forecasting a time series from multivariate predictors constitutes a challenging problem, especially using model-free approaches. Most techniques, such as nearest-neighbor prediction, quickly suffer from the curse of dimensionality and overfitting for more than a few predictors which has limited their application mostly to the univariate case. Therefore, selection strategies are needed that harness the available information as efficiently as possible. Since often the right combination of predictors matters, ideally all subsets of possible predictors should be tested for their predictive power, but the exponentially growing number of combinations makes such an approach computationally prohibitive. Here a prediction scheme that overcomes this strong limitation is introduced utilizing a causal pre-selection step which drastically reduces the number of possible predictors to the most predictive set of causal drivers making a globally optimal search scheme tractable. The information-theoretic optimality is derived and practical selection criteria are discussed. As demonstrated for multivariate nonlinear stochastic delay processes, the optimal scheme can even be less computationally expensive than commonly used sub-optimal schemes like forward selection. The method suggests a general framework to apply the optimal model-free approach to select variables and subsequently fit a model to further improve a prediction or learn statistical dependencies. The performance of this framework is illustrated on a climatological index of El Ni\~no Southern Oscillation.

In order to investigate the breast cancer prediction problem on the aging population with the grades of DCIS, we conduct a tree augmented naive Bayesian network experiment trained and tested on a large clinical dataset including consecutive diagnostic mammography examinations, consequent biopsy outcomes and related cancer registry records in the population of women across all ages. The aggregated results of our ten-fold cross validation method recommend a biopsy threshold higher than 2% for the aging population.