Abstract

Reinforcement Learning provides an attractive suite of online learning methods for person

In the big data era, it is necessary to rely on distributed computing. For distributed optimization and learning tasks, in particular in the modern paradigm of federated learning, specific challenges arise, such as decentralized data storage. Communication between the parallel machines and the orchestrating distant server is necessary but slow. To address this main bottleneck, a natural strategy is to compress the communicated vectors. I will present EF-BV, a new algorithm which converges linearly to an exact solution, with a large class of deterministic or random, biased or unbiased compressors.

Random fields are popular models in statistics and machine learning for spatially dependent data on Euclidian domains. However, in many applications, data is observed on non-Euclidian domains such as street networks. In this case, it is much more difficult to construct valid random field models. In this talk, we discuss some recent approaches to modeling data in this setting, and in particular define a new class of Gaussian processes on compact metric graphs.

This talk will focus on challenges and opportunities in designing middleware for HPC, AI (Deep/Machine Learning), and Data Science. We will start with the challenges in designing runtime environments for MPI+X programming models by considering support for multi-core systems, high-performance networks (InfiniBand and RoCE), GPUs, and emerging BlueField-2 DPUs. Features and sample performance numbers of using the MVAPICH2 libraries will be presented. For the Deep/Machine Learning domain, we will focus on MPI-driven solutions to extract performance and scalability for popular Deep Learning frameworks (TensorFlow and PyTorch), large out-of-core models, and Bluefield-2 DPUs.

Machine perception that corresponds to the ability to understand the visual world based on the input from sensors, such as cameras is one of the central problems in Artificial Intelligence. To this end, recent years have witnessed tremendous progress in various instance-level recognition tasks having real-world applications in e.g., robotics, autonomous driving and surveillance. In this talk, I will first present our recent results towards understanding state-of-the-art deep learning-based visual recognition networks in terms of their robustness and generalizability. Next, I will present our results on learning visual recognition models with limited human supervision. Finally, I will discuss moving one step further from instance-level recognition to understand visual relationships between object pairs.

In this thesis, we discuss a few fundamental and well-studied optimization problem classes: decentralized distributed optimization (Chapters 2 to 4), distributed optimization under similarity (Chapter 5), affinely constrained optimization (Chapter 6), minimax optimization (Chapter 7), and high-order optimization (Chapter 8). For each problem class, we develop the first provably optimal algorithm: the complexity of such an algorithm cannot be improved for the problem class given. The proposed algorithms show state-of-the-art performance in practical applications, which makes them highly attractive for potential generalizations and extensions in the future.

In this talk, I will start by providing our vision for next-generation networks. Throughout the talk, I will highlight several challenges in existing communication technologies that could have the potential of shaping new research and deployment directions of future wireless networks, including, (i) review our recent advances in non-terrestrial networks, which includes both UAVs and satellite (ii) show satellite systems are essential for today’s traffic-intensive applications while maintaining an accepted end-to-end latency for delay-sensitive applications and (iii) show how we integrated both existing Wi-Fi technology with optics to extend the Internet as we use it today to the underwater environments via Aqua-fi.

This talks presents a very serious emerging threat: the bots scraping web sites and hiding their IPs thanks to residential IP providers. The problem, state of the art and a new solution will be explained.

In this talk, I will discuss communication compression and aggregation mechanisms for curvature information in order to reduce these costs while preserving theoretically superior local convergence guarantees.

In a nutshell, Resilient Computing is a new paradigm based on modelling, architecting and designing computer systems so that: they have built-in baseline defences; such defences cope with virtually any quality of threat, be it accidental faults, design errors, cyber-attacks, or unexpected operating conditions; provide incremental protection of, and automatically adapt to, a dynamic range of threat severity; provide sustainable operation.

This talk presents some perspectives on doing research in computer science and publishing through the peer review process.

In this dissertation, we combined artificial intelligence and machine/deep learning with chemical and biological properties to develop several computational methods to solve biomedical domain problems, specifically drug repositioning, and demonstrated their efficiencies and capabilities. We developed three network-based DTI prediction methods using machine learning, graph embedding, and graph mining. These methods significantly improved prediction performance, and the best-performing method even reduces the error rate by more than 33% across all datasets compared to the best state-of-the-art method. As it is more insightful to predict continuous values that indicate how tightly the drug binds to a specific target, we conducted a comparison study of current regression-based methods that predict drug-target binding affinities (DTBA). Our methods demonstrated their efficiency and capability by achieving high prediction performance and identifying therapeutic targets for several cancer types. We further conducted a lung cancer case study of findings that support the novel predicted targets.

One of the key drivers for next-generation mobile communications is the support of the Internet of Things (IoT), with billions of objects connected to the Internet and very low latency. The 5G technology will support the realization of smart cities, smart environments, and big data applications.

Scientific applications from diverse sources rely on dense matrix operations. These operations arise in: Schur complements, integral equations, covariances in spatial statistics, ridge regression, radial basis functions from unstructured meshes, and kernel matrices from machine learning, among others. This thesis demonstrates how to extend the problem sizes that may be treated and reduce their execution time. Sometimes, even forming the dense matrix can be a bottleneck – in computation or storage.

This talk will present our recent research works related to the application of data science in the environment, healthcare, and social media.

Critical Infrastructures (CIs) are the cornerstone Economics and Society rely upon. In this talk, we will start with surveying some of the threats different CIs are subject to, highlighting some research problems and related results.

Datasets that capture the connection between vision, language, and affection are limited, causing a lack of understanding of the emotional aspect of human intelligence. As a step in this direction, the ArtEmis dataset was recently introduced as a large-scale dataset of emotional reactions to images along with language explanations of these chosen emotions.

This course aims to familiarize students with the Computer Simulation tools for complex problems. The course will introduce the basic concepts of computation through modeling and simulation that are increasingly being used in industry and academia. The basic concepts of Discrete Event Simulation will be introduced along with the reliable methods of random variate generation. Later in the course, the concept of simulation-based optimization will be discussed, introducing an overview of various optimization approaches. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed. The last lecture will be devoted to the contemporary topics in simulation.

Hydrogen is a carbon-free energy carrier that can be used to decarbonize various high-emitting sectors, such as transportation, power generation, and industry. Today, global hydrogen production is largely derived from fossil fuels such as natural gas and coal.

This course aims to familiarize students with the Computer Simulation tools for complex problems. The course will introduce the basic concepts of computation through modeling and simulation that are increasingly being used in industry and academia. The basic concepts of Discrete Event Simulation will be introduced along with the reliable methods of random variate generation. Later in the course, the concept of simulation-based optimization will be discussed, introducing an overview of various optimization approaches. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed. The last lecture will be devoted to the contemporary topics in simulation.

This course aims to familiarize students with the Computer Simulation tools for complex problems. The course will introduce the basic concepts of computation through modeling and simulation that are increasingly being used in industry and academia. The basic concepts of Discrete Event Simulation will be introduced along with the reliable methods of random variate generation. Later in the course, the concept of simulation-based optimization will be discussed, introducing an overview of various optimization approaches. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed. The last lecture will be devoted to the contemporary topics in simulation.

Differential Privacy (DP) allows for rich statistical and machine learning analysis, and is now becoming a gold standard for private data analysis. Despite the noticeable success of this theory, existing tools from DP are severely limited to regular datasets, e.g., datasets need to be or are assumed to be clean and normalized before performing DP algorithms.

The power system is facing unprecedented changes in operation and control as more and diverse sources and loads are being connected to this complex cyber-physical energy system.

Geospatial health data are essential to inform public health and policy. These data can be used to quantify disease burden, understand geographic and temporal patterns, identify risk factors and measure inequalities. In this talk, I will give an overview of statistical methods and computational tools for geospatial data analysis and health surveillance.

In this thesis, we investigate how learning-based approaches are implemented to solve the communication network problems and how communication network dependencies impact the training of learning-based approaches.