With an eye towards human-centered automation, we contribute to the development of a systematic means to infer features of human decision-making from behavioral data. Motivated by the common use of softmax selection in models of human decision-making, we study the maximum likelihood parameter estimation problem for softmax decision-making models with linear objective functions. We present conditions under which the likelihood function is convex. These allow us to provide sufficient conditions for convergence of the resulting maximum likelihood estimator and to construct its asymptotic distribution. In the case of models with nonlinear objective functions, we show how the estimator can be applied by linearizing about a nominal parameter value. We apply the estimator to fit the stochastic UCL (Upper Credible Limit) model of human decision-making to human subject data. We show statistically significant differences in behavior across related, but distinct, tasks.

In most adaptive signal processing applications, system linearity is assumed and adaptive linear filters are thus used. The traditional class of supervised adaptive filters rely on error-correction learning for their adaptive capability. The kernel method is a powerful nonparametric modeling tool for pattern analysis and statistical signal processing. Through a nonlinear mapping, kernel methods transform the data into a set of points in a Reproducing Kernel Hilbert Space. KRLS achieves high accuracy and has fast convergence rate in stationary scenario. However the good performance is obtained at a cost of high computation complexity. Sparsification in kernel methods is know to related to less computational complexity and memory consumption.

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability problems for large-scale applications, forcing researchers or users to focus on smallscale problems with fewer parameters. In this paper, we consider a well-known machine learning model, deep belief networks (DBNs) that have yielded impressive classification performance on a large number of benchmark machine learning tasks. To scale up DBN, we propose an approach that can use the computing clusters in a distributed environment to train large models, while the dense matrix computations within a single machine are sped up using graphics processors (GPU). When training a DBN, each machine randomly drops out a portion of neurons in each hidden layer, for each training case, making the remaining neurons only learn to detect features that are generally helpful for producing the correct answer. Within our approach, we have developed four methods to combine outcomes from each machine to form a unified model. Our preliminary experiment on the MNIST handwritten digit database demonstrates that our approach outperforms the state of the art test error rate.

Clustering, the problem of partitioning observations with high intragroup similarity, has always been one of the central themes in unsupervised learning. Although a wide variety of algorithms for clustering applications have been studied in literature, the subject still remains an active avenue for research. In fact, it is possible to formulate clustering as a matrix decomposition problem. This formulation leads to interesting interpretations as well as novel algorithms that benefit from favorable computational properties of numerical linear algebra. Popularized by Lee and Seung [11], Nonnegative Matrix Factorization (NMF) has turned into one of the primary tools for decomposing data sets into low-rank factorizing matrices in order to yield a parts-based representation.

Dirichlet Process(DP) is a Bayesian non-parametric prior for infinite mixture modeling, where the number of mixture components grows with the number of data items. The Hierarchical Dirichlet Process (HDP), is an extension of DP for grouped data, often used for non-parametric topic modeling, where each group is a mixture over shared mixture densities. The Nested Dirichlet Process (nDP), on the other hand, is an extension of the DP for learning group level distributions from data, simultaneously clustering the groups. It allows group level distributions to be shared across groups in a non-parametric setting, leading to a non-parametric mixture of mixtures. The nCRF extends the nDP for multilevel non-parametric mixture modeling, enabling modeling topic hierarchies. However, the nDP and nCRF do not allow sharing of distributions as required in many applications, motivating the need for multi-level non-parametric admixture modeling. We address this gap by proposing multi-level nested HDPs (nHDP) where the base distribution of the HDP is itself a HDP at each level thereby leading to admixtures of admixtures at each level. Because of couplings between various HDP levels, scaling up is naturally a challenge during inference. We propose a multi-level nested Chinese Restaurant Franchise (nCRF) representation for the nested HDP, with which we outline an inference algorithm based on Gibbs Sampling. We evaluate our model with the two level nHDP for non-parametric entity topic modeling where an inner HDP creates a countably infinite set of topic mixtures and associates them with author entities, while an outer HDP associates documents with these author entities. In our experiments on two real world research corpora, the nHDP is able to generalize significantly better than existing models and detect missing author entities with a reasonable level of accuracy.

We investigate a Gaussian mixture model (GMM) with component means constrained in a pre-selected subspace. Applications to classification and clustering are explored. An EM-type estimation algorithm is derived. We prove that the subspace containing the component means of a GMM with a common covariance matrix also contains the modes of the density and the class means. This motivates us to find a subspace by applying weighted principal component analysis to the modes of a kernel density and the class means. To circumvent the difficulty of deciding the kernel bandwidth, we acquire multiple subspaces from the kernel densities based on a sequence of bandwidths. The GMM constrained by each subspace is estimated; and the model yielding the maximum likelihood is chosen. A dimension reduction property is proved in the sense of being informative for classification or clustering. Experiments on real and simulated data sets are conducted to examine several ways of determining the subspace and to compare with the reduced rank mixture discriminant analysis (MDA). Our new method with the simple technique of spanning the subspace only by class means often outperforms the reduced rank MDA when the subspace dimension is very low, making it particularly appealing for visualization.

The extensive use of private and personally identifiable information in modern statistical (and machine learning) applications can present an obstacle to individuals contributing their data to research. As just one example, when considering contribution to biobanks Kaufman et al. (2009) reported 90% of respondents had privacy concerns. Addressing these concerns is paramount if the participation rate in biomedical and genetic research is to be increased, especially for government and industry where public trust is lower (Kaufman et al., 2009). Indeed, industry is on the brink on embarking on biomedical applications on a scale never before witnessed via the impending wave of so-called'wearable devices' such as smart watches, which present serious privacy concerns. Companies hope to market the ability to monitor and track vital health signs round the clock, perhaps fitting classification models to alert different health concerns of interest.

A recurring problem when building probabilistic latent variable models is regularization and model selection, for instance, the choice of the dimensionality of the latent space. In the context of belief networks with latent variables, this problem has been adressed with Automatic Relevance Determination (ARD) employing Monte Carlo inference. We present a variational inference approach to ARD for Deep Generative Models using doubly stochastic variational inference to provide fast and scalable learning. We show empirical results on a standard dataset illustrating the effects of contracting the latent space automatically. We show that the resulting latent representations are significantly more compact without loss of expressive power of the learned models.

In this paper we consider the training of single hidden layer neural networks by pseudoinversion, which, in spite of its popularity, is sometimes affected by numerical instability issues. Regularization is known to be effective in such cases, so that we introduce, in the framework of Tikhonov regularization, a matricial reformulation of the problem which allows us to use the condition number as a diagnostic tool for identification of instability. By imposing well-conditioning requirements on the relevant matrices, our theoretical analysis allows the identification of an optimal value for the regularization parameter from the standpoint of stability. We compare with the value derived by cross-validation for overfitting control and optimisation of the generalization performance. We test our method for both regression and classification tasks. The proposed method is quite effective in terms of predictivity, often with some improvement on performance with respect to the reference cases considered. This approach, due to analytical determination of the regularization parameter, dramatically reduces the computational load required by many other techniques.

We consider statistical as well as algorithmic aspects of solving large-scale least-squares (LS) problems using randomized sketching algorithms. For a LS problem with input data $(X, Y) \in \mathbb{R}^{n \times p} \times \mathbb{R}^n$, sketching algorithms use a sketching matrix, $S\in\mathbb{R}^{r \times n}$ with $r \ll n$. Then, rather than solving the LS problem using the full data $(X,Y)$, sketching algorithms solve the LS problem using only the sketched data $(SX, SY)$. Prior work has typically adopted an algorithmic perspective, in that it has made no statistical assumptions on the input $X$ and $Y$, and instead it has been assumed that the data $(X,Y)$ are fixed and worst-case (WC). Prior results show that, when using sketching matrices such as random projections and leverage-score sampling algorithms, with $p < r \ll n$, the WC error is the same as solving the original problem, up to a small constant. From a statistical perspective, we typically consider the mean-squared error performance of randomized sketching algorithms, when data $(X, Y)$ are generated according to a statistical model $Y = X \beta + \epsilon$, where $\epsilon$ is a noise process. We provide a rigorous comparison of both perspectives leading to insights on how they differ. To do this, we first develop a framework for assessing algorithmic and statistical aspects of randomized sketching methods. We then consider the statistical prediction efficiency (PE) and the statistical residual efficiency (RE) of the sketched LS estimator; and we use our framework to provide upper bounds for several types of random projection and random sampling sketching algorithms. Among other results, we show that the RE can be upper bounded when $p < r \ll n$ while the PE typically requires the sample size $r$ to be substantially larger. Lower bounds developed in subsequent results show that our upper bounds on PE can not be improved.