Best papers of the workshop, after further revisions and independent reviews, will be considered for publication in a special issue of a renowned journal. By this holistic view we encounter a variety of challenges along the AI modeling cycle and software system engineering lifecycle as outlined in the figure below such as: • theory-practice gap in machine learning with impact on stability, reproducibility or integrity due to limitations of nowadays theoretical foundations in statistical learning theory or lack of control of high-dimensionality effects of deep learning; • facing computational constraints, e.g. All submissions will be peer-reviewed by, at least, 3 reviewers and judged on the basis of originality, contribution to the field, technical and presentation quality, and relevance to the workshop. Short papers are meant for timely discussion and feedback at the workshop. Papers are accepted with the understanding that at least one author will register for the conference to present the paper.

Data science is an interdisciplinary field that uses scientific methods, processes, and algorithms to extract knowledge and insights from data. The field of data science has several subdivisions such as data mining, data transformation, data visualization, machine learning, deep learning, etc. This is the stage where data is collected, analyzed to unravel patterns and relationships in the data, and questions are asked to be answered using the data. This is where mathematical skills come into play. In this stage, mathematical tools are used to build models (predictive models) for quantifying patterns or studying the relationships between features in the dataset.

We study the problem of adaptive control of the linear quadratic regulator for systems in very high, or even infinite dimension. We demonstrate that while sublinear regret requires finite dimensional inputs, the ambient state dimension of the system need not be bounded in order to perform online control. We provide the first regret bounds for LQR which hold for infinite dimensional systems, replacing dependence on ambient dimension with more natural notions of problem complexity. Our guarantees arise from a novel perturbation bound for certainty equivalence which scales with the prediction error in estimating the system parameters, without requiring consistent parameter recovery in more stringent measures like the operator norm. When specialized to finite dimensional settings, our bounds recover near optimal dimension and time horizon dependence.

Inductive inference in supervised classification context constitutes to methods and approaches to assign some objects or items into different predefined classes using a formal rule that is derived from training data and possibly some additional auxiliary information. The optimality of such an assignment varies under different conditions due to intrinsic attributes of the objects being considered for such a task. One of these cases is when all the objects' features are discrete variables with a priori known categories. As another example, one can consider a modification of this case with a priori unknown categories. These two cases are the main focus of this thesis and based on Bayesian inductive theories, de Finetti type exchangeability is a suitable assumption that facilitates the derivation of classifiers in the former scenario. On the contrary, this type of exchangeability is not applicable in the latter case, instead, it is possible to utilise the partition exchangeability due to John Kingman. These two types of exchangeabilities are discussed and furthermore here I investigate inductive supervised classifiers based on both types of exchangeabilities. I further demonstrate that the classifiers based on de Finetti type exchangeability can optimally handle test items independently of each other in the presence of infinite amounts of training data while on the other hand, classifiers based on partition exchangeability still continue to benefit from joint labelling of all the test items. Additionally, it is shown that the inductive learning process for the simultaneous classifier saturates when the amount of test data tends to infinity.

Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge. In this paper, we propose two timescale hybrid federated learning (TT-HF), which is a hybrid between the device-to-server communication paradigm in federated learning and device-to-device (D2D) communications for model training. In TT-HF, during each global aggregation interval, devices (i) perform multiple stochastic gradient descent iterations on their individual datasets, and (ii) aperiodically engage in consensus formation of their model parameters through cooperative, distributed D2D communications within local clusters. With a new general definition of gradient diversity, we formally study the convergence behavior of TT-HF, resulting in new convergence bounds for distributed ML. We leverage our convergence bounds to develop an adaptive control algorithm that tunes the step size, D2D communication rounds, and global aggregation period of TT-HF over time to target a sublinear convergence rate of O(1/t) while minimizing network resource utilization. Our subsequent experiments demonstrate that TT-HF significantly outperforms the current art in federated learning in terms of model accuracy and/or network energy consumption in different scenarios where local device datasets exhibit statistical heterogeneity.

Mechanistic models with differential equations are a key component of scientific applications of machine learning. Inference in such models is usually computationally demanding, because it involves repeatedly solving the differential equation. The main problem here is that the numerical solver is hard to combine with standard inference techniques. Recent work in probabilistic numerics has developed a new class of solvers for ordinary differential equations (ODEs) that phrase the solution process directly in terms of Bayesian filtering. We here show that this allows such methods to be combined very directly, with conceptual and numerical ease, with latent force models in the ODE itself. It then becomes possible to perform approximate Bayesian inference on the latent force as well as the ODE solution in a single, linear complexity pass of an extended Kalman filter / smoother - that is, at the cost of computing a single ODE solution. We demonstrate the expressiveness and performance of the algorithm by training a non-parametric SIRD model on data from the COVID-19 outbreak.

This study presents PRISM, a probabilistic simplex component analysis approach to identifying the vertices of a data-circumscribing simplex from data. The problem has a rich variety of applications, the most notable being hyperspectral unmixing in remote sensing and non-negative matrix factorization in machine learning. PRISM uses a simple probabilistic model, namely, uniform simplex data distribution and additive Gaussian noise, and it carries out inference by maximum likelihood. The inference model is sound in the sense that the vertices are provably identifiable under some assumptions, and it suggests that PRISM can be effective in combating noise when the number of data points is large. PRISM has strong, but hidden, relationships with simplex volume minimization, a powerful geometric approach for the same problem. We study these fundamental aspects, and we also consider algorithmic schemes based on importance sampling and variational inference. In particular, the variational inference scheme is shown to resemble a matrix factorization problem with a special regularizer, which draws an interesting connection to the matrix factorization approach. Numerical results are provided to demonstrate the potential of PRISM.

Sequentially obtained dataset usually exhibits different behavior at different data resolutions/scales. Instead of inferring from data at each scale individually, it is often more informative to interpret the data as an ensemble of time series from different scales. This naturally motivated us to propose a new concept referred to as the scale-based inference. The basic idea is that more accurate prediction can be made by exploiting scale information of a time series. We first propose a nonparametric predictor based on $k$-nearest neighbors with an optimally chosen $k$ for a single time series. Based on that, we focus on a specific but important type of scale information, the resolution/sampling rate of time series data. We then propose an algorithm to sequentially predict time series using past data at various resolutions. We prove that asymptotically the algorithm produces the mean prediction error that is no larger than the best possible algorithm at any single resolution, under some optimally chosen parameters. Finally, we establish the general formulations for scale inference, and provide further motivating examples. Experiments on both synthetic and real data illustrate the potential applicability of our approaches to a wide range of time series models.

Nowadays online users prefer to join multiple social media for the purpose of socialized online service. The problem \textit{anchor link prediction} is formalized to link user data with the common ground on user profile, content and network structure across social networks. Most of the traditional works concentrated on learning matching function with explicit or implicit features on observed user data. However, the low quality of observed user data confuses the judgment on anchor links, resulting in the matching collision problem in practice. In this paper, we explore local structure consistency and then construct a matching graph in order to circumvent matching collisions. Furthermore, we propose graph convolution networks with mini-batch strategy, efficiently solving anchor link prediction on matching graph. The experimental results on three real application scenarios show the great potentials of our proposed method in both prediction accuracy and efficiency. In addition, the visualization of learned embeddings provides us a qualitative way to understand the inference of anchor links on the matching graph.

We consider a novel data driven approach for designing learning algorithms that can effectively learn with only a small number of labeled examples. This is crucial for modern machine learning applications where labels are scarce or expensive to obtain. We focus on graph-based techniques, where the unlabeled examples are connected in a graph under the implicit assumption that similar nodes likely have similar labels. Over the past decades, several elegant graph-based semi-supervised and active learning algorithms for how to infer the labels of the unlabeled examples given the graph and a few labeled examples have been proposed. However, the problem of how to create the graph (which impacts the practical usefulness of these methods significantly) has been relegated to domain-specific art and heuristics and no general principles have been proposed. In this work we present a novel data driven approach for learning the graph and provide strong formal guarantees in both the distributional and online learning formalizations. We show how to leverage problem instances coming from an underlying problem domain to learn the graph hyperparameters from commonly used parametric families of graphs that perform well on new instances coming from the same domain. We obtain low regret and efficient algorithms in the online setting, and generalization guarantees in the distributional setting. We also show how to combine several very different similarity metrics and learn multiple hyperparameters, providing general techniques to apply to large classes of problems. We expect some of the tools and techniques we develop along the way to be of interest beyond semi-supervised and active learning, for data driven algorithms for combinatorial problems more generally.