Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian optimization. However, to practically enable automated tuning for large scale machine learning training pipelines, significant gaps remain in existing libraries, including lack of abstractions, fault tolerance, and flexibility to support scheduling on any distributed computing framework. To address these challenges, we present Mango, a Python library for parallel hyperparameter tuning. Mango enables the use of any distributed scheduling framework, implements intelligent parallel search strategies, and provides rich abstractions for defining complex hyperparameter search spaces that are compatible with scikit-learn. Mango is comparable in performance to Hyperopt, another widely used library. Mango is available open-source and is currently used in production at Arm Research to provide state-of-art hyperparameter tuning capabilities.

Hierarchical modeling and learning has proven very powerful in the field of Gaussian process regression and kernel methods, especially for machine learning applications and, increasingly, within the field of inverse problems more generally. The classical approach to learning hierarchical information is through Bayesian formulations of the problem, implying a posterior distribution on the hierarchical parameters or, in the case of empirical Bayes, providing an optimization criterion for them. Recent developments in the machine learning literature have suggested new criteria for hierarchical learning, based on approximation theoretic considerations that can be interpreted as variants of cross-validation, and exploiting approximation consistency in data splitting. The purpose of this paper is to compare the empirical Bayesian and approximation theoretic approaches to hierarchical learning, in terms of large data consistency, variance of estimators, robustness of the estimators to model misspecification, and computational cost. Our analysis is rooted in the setting of Mat\'ern-like Gaussian random field priors, with smoothness, amplitude and inverse lengthscale as hierarchical parameters, in the regression setting. Numerical experiments validate the theory and extend the scope of the paper beyond the Mat\'ern setting.

Several public security systems depend directly on human action in numerous stages of its operation. The monitoring of public areas, for instance, is usually done with the use of cameras spread over the busiest places in large urban centers. In general, these systems depend on an operator to pay attention to the images so that the agencies responsible for security can be activated when events such as thefts, vandalism, and traffic accidents are observed. Considering the amount of information to which the operator is exposed, there is a high probability that surveillance failures will occur, even if the patrol center has a large team [1]. Although the operators are attentive at all times, this type of monitoring has some disadvantages: the images are limited to the direction in which the camera points and have low visibility at dusk and in cases of rain or bright light. Besides, events such as gunshots, alarms, distress calls, among others, are much more noticeable in the auditory field than in the visual [2, 3]. In this sense, the monitoring of risk areas could be done through the use of audio processing techniques, reducing the need for human participation in the surveillance process, and making public security systems more efficient [4]. To support this argument, it is worth recalling two very favorable characteristics concerning these signals: initially, the sound consumes less bandwidth in the transmission of information, reducing the need for high transmission rates, as in the case of high definition images; in addition, sound processing techniques require, in general, less computational power than techniques for video processing and analysis, which would enable the implementation of simpler and therefore less costly embedded systems [3, 5].

This study aims to provide a comparative analysis of performance of certain models popular in machine learning and the BERT model on the Stanford Question Answering Dataset (SQuAD). The analysis shows that the BERT model, which was once state-of-the-art on SQuAD, gives higher accuracy in comparison to other models. However, BERT requires a greater execution time even when only 100 samples are used. This shows that with increasing accuracy more amount of time is invested in training the data. Whereas in case of preliminary machine learning models, execution time for full data is lower but accuracy is compromised.

Inverse probability weighted estimators are the oldest and potentially most commonly used class of procedures for the estimation of causal effects. By adjusting for selection biases via a weighting mechanism, these procedures estimate an effect of interest by constructing a pseudo-population in which selection biases are eliminated. Despite their ease of use, these estimators require the correct specification of a model for the weighting mechanism, are known to be inefficient, and suffer from the curse of dimensionality. We propose a class of nonparametric inverse probability weighted estimators in which the weighting mechanism is estimated via undersmoothing of the highly adaptive lasso, a nonparametric regression function proven to converge at $n^{-1/3}$-rate to the true weighting mechanism. We demonstrate that our estimators are asymptotically linear with variance converging to the nonparametric efficiency bound. Unlike doubly robust estimators, our procedures require neither derivation of the efficient influence function nor specification of the conditional outcome model. Our theoretical developments have broad implications for the construction of efficient inverse probability weighted estimators in large statistical models and a variety of problem settings. We assess the practical performance of our estimators in simulation studies and demonstrate use of our proposed methodology with data from a large-scale epidemiologic study.

This paper studies a high-dimensional inference problem involving the matrix tensor product of random matrices. This problem generalizes a number of contemporary data science problems including the spiked matrix models used in sparse principal component analysis and covariance estimation. It is shown that the information-theoretic limits can be described succinctly by formulas involving low-dimensional quantities. On the technical side, this paper introduces some new techniques for the analysis of high-dimensional matrix-valued signals. Specific contributions include a novel extension of the adaptive interpolation method that uses order-preserving positive semidefinite interpolation paths and a variance inequality based on continuous-time I-MMSE relations.

We study supervised learning by extreme learning machines and regression for autonomous objects moving in a non-stationary spatial environment. In general, this results in non-stationary data in contrast to the i.i.d. sampling typically studied in learning theory. The stochastic model for the environment and data collection especially allows for algebraically decaying weak dependence and spatial heterogeneity, for example induced by interactions of the object with sources of randomness spread over the spatial domain. Both least squares and ridge learning as a computationally cheap regularization method is studied. Consistency and asymptotic normality of the least squares and ridge regression estimates is shown under weak conditions. The results also cover consistency in terms of bounds for the sample squared predicition error. Lastly, we discuss a resampling method to compute confidence regions.

Discovering patterns of the complex high-dimensional data is a long-standing problem. Dimension Reduction (DR) and Intrinsic Dimension Estimation (IDE) are two fundamental thematic programs that facilitate geometric understanding of the data. We present Rdimtools - an R package that supports 133 DR and 17 IDE algorithms whose extent makes multifaceted scrutiny of the data in one place easier. Rdimtools is distributed under the MIT license and is accessible from CRAN, GitHub, and its package website, all of which deliver instruction for installation, self-contained examples, and API documentation.

In this paper, novel gradient based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, the location and the released time of a river pollution source based on downstream sensor data monitoring the pollution concentration. The problem can be formulated as a non-convex loss minimization problem in statistical learning, and our online algorithms have vectorized and adaptive step-sizes to ensure high estimation accuracy on dimensions having different magnitudes. In order to avoid gradient-based method sticking into the saddle points of non-convex loss, the "escaping from saddle points" module and multi-start version of algorithms are derived to further improve the estimation accuracy by searching for the global minimimals of the loss functions. It can be shown theoretically and experimentally $O(N)$ local regret of the algorithms, and the high probability cumulative regret bound $O(N)$ under particular error bound condition on loss functions. A real-life river pollution source identification example shows superior performance of our algorithms than the existing methods in terms of estimating accuracy. The managerial insights for decision maker to use the algorithm in reality are also provided.

We consider the problem of jointly estimating multiple related zero-mean Gaussian distributions from data. We propose to jointly estimate these covariance matrices using Laplacian regularized stratified model fitting, which includes loss and regularization terms for each covariance matrix, and also a term that encourages the different covariances matrices to be close. This method `borrows strength' from the neighboring covariances, to improve its estimate. With well chosen hyper-parameters, such models can perform very well, especially in the low data regime. We propose a distributed method that scales to large problems, and illustrate the efficacy of the method with examples in finance, radar signal processing, and weather forecasting.