Entrepreneurs continue to be the driver for economic development and innovation. Some startups invent brand new markets while other manage to enter markets crowded by existing large companies. In this seminar we will explore making critical early decisions starting from chaos and creating an exciting new business. We will gain insights on the value of learning by doing, prototyping, discussing tradeoffs between analysis, experimentation and scale.  We will also review courses offered by KAUST Entrepreneurship Center.

In reaction to the waning benefit of transistor scaling and the increasing demands on computing power, specialized accelerators have drawn significant attention from both academics and industry because of their orders-of-magnitude performance improvement and energy efficiency. All these accelerators require non-trivial human efforts, from designing the architecture to having a full-stack implementation. Therefore, the software/hardware co-designed innovations are often monopolized by several large teams in large companies. In this talk, I will first discuss how my research democratizes the accelerator designs and unifies the hardware/software innovations by automating the accelerator design process under a unified programming paradigm. By taking advantage of the compiler’s awareness of the program behaviors that profit from hardware specialization, accelerators can be automatically synthesized by searching through a well-defined design space. These automatically designed accelerators achieve comparable cost/performance efficiency compared with prior handcrafted designs. In the rest of the talk, I will also cover how this work inspires me to develop techniques to accelerate emerging application domains by orders-of-magnitude speedup, including digital signal processing and DNN inference, and how I take advantage of this work to revolutionize the FPGA programming paradigm.

Vulnerability discovery can be challenging: many software packages, both open and closed-source projects, build on existing code from public software repositories to network drives, derived from earlier versions or related software packages. Even implemented protocols rely on such repositories. It is important to detect such copies of code when the original code contains a software vulnerability, especially one that is exploitable, as seen with flaws such as the bash vulnerability Shellshock or the SSL vulnerability Heartbleed.

In this talk we first provide an introduction to point processes, which are stochastic models for the occurrence of events in space and time. We then discuss the application of point processes to investigate the relationship between law enforcement drug seizures and accidental overdoses in Indianapolis. We will also discuss results from a field-experiment in Indianapolis where point process based harm indices were used to inform the distribution of addiction treatment information. 

Machine Learning (ML) tools have recently been adopted for a wide range of automated operations in optical networking, moving fundamental steps towards the paradigm of zero-touch infrastructures. One example of such tasks is estimating the Quality of transmission of a lightpath prior to its establishment, which is particularly challenging due to the non-linear characteristics of signal propagation in optical fibers and to the often-incomplete knowledge of equipment parameters. This talk provides an overview of the contribution of my research team in the field of ML-based lightpath QoT estimation, including transfer learning approaches for inter-domain model adaptation, active learning for model building with small-sized training dataset, quantification of prediction uncertainty, and adoption of Explainable AI framework to expose the internal decisional mechanisms of trained models.

In this work we focus our attention on distributed optimization problems in the context where the communication time between the server and the workers is non-negligible. We obtain novel methods supporting bidirectional compression (both from the server to the workers and vice versa) that enjoy new state-of-the-art theoretical communication complexity for convex and nonconvex problems.

In this talk we will explore how research in systems and distributed systems may improve the resilience to cyber attacks following 3 axes targeting mobile systems, distributed systems, and operating systems

In this talk, we will define prototypical random walks, a mechanism we introduced to improve visual classification with limited data (few-shot learning), and then developed the mechanism in a conceptually different way to facilitate novel image generation and unseen class recognition tasks. More specifically, in the few-shot learning setting, we will show how we can develop a random walk semi-supervised loss that enables the network to learn representations that are compact and well-separated.

I will discuss four related proposals: Gracewipe (coercion-resistant disk data deletion), Hypnoguard (cold-boot protection for RAM data in sleep), SafeKeeper (protecting web credentials from rougue IT admins), and Blindfold (protecting PKI private keys from human admins). While our solutions are possibly a step forward, more importantly, we highlight pitfalls of such solutions against a strong adversary.

With video data dominating the internet traffic, it is crucial to develop automated models that can analyze and understand what humans do in videos. Such models must solve tasks such as action classification, temporal activity localization, spatiotemporal action detection, and video captioning. This dissertation aims to identify the challenges hindering the progress in human action understanding and propose novel solutions to overcome these challenges.

Trusted Execution Environments (TEEs) ensure the confidentiality and integrity of computations in hardware. Subject to the TEE's threat model, the hardware shields a computation from most externally induced fault behavior except crashes. As a result, a crash-fault tolerant (CFT) replication protocol should be sufficient when replicating trusted code inside TEEs.  However, TEEs do not provide efficient and general means of ensuring the freshness of the external, persistent state. Therefore, CFT replication is insufficient for TEE computations with an external state, as this state could be rolled back to an earlier version when a TEE restarts.  Furthermore, using BFT protocols in this setting is too conservative, because these protocols are designed to tolerate arbitrary behavior, not just rollback during a restart.

Building on the work of Schöberl, Olshanskii, and Benzi, in this talk we present the first preconditioner for the Newton linearization of the stationary Navier--Stokes equations in three dimensions that achieve both optimal complexity in of count and Reynolds-robustness. The exact details of the preconditioner varies with discretization, but the general theme is to combine augmented Lagrangian stabilisation, a custom multigrid prolongation operator involving local solves on coarse cells, and an additive patchwise relaxation on each level that captures the kernel of the divergence operator.

This seminar focuses on providing the audience with the context and scope of our internship program. The program is for the young and talented graduate students with an active interest in solving real-world problems. Some of the projects that will be presented in the seminar are actively developed in Elm and include domains such as computer vision, robotics and automation, healthcare, IoT, video analytics, and NLP. The seminar will serve as a launch pad to allow students to discuss their future interests and aspirations with the speaker. It will also enable them to develop a better awareness of domains more relevant to their future research aspirations.

In this talk, I will first give a convergence analysis of gradient descent (GD) method for training neural networks by relating them with finite element method. I will then present some acceleration techniques for GD method and also give some alternative training algorithms

Parameter-free online optimization is a class of algorithms that does not require tuning hyperparameters, yet they achieve the theoretical optimal performance. Moreover, they often achieve state-of-the-art performance too. An example would be gradient descent algorithms completely without learning rates. In this talk, I review my past and present contributions to this field. Building upon a fundamental idea connecting optimization, gambling, and information theory, I discuss selected applications of parameter-free algorithms to machine learning and statistics. Finally, we conclude with an overview of the future directions of this field.

The aim of this course is to familiarize the students with the usage of 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 and variance reduction. Later in the course, the concept of simulation-based optimization and output analysis will be discussed. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed.

The aim of this course is to familiarize the students with the usage of 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 and variance reduction. Later in the course, the concept of simulation-based optimization and output analysis will be discussed. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed.

The aim of this course is to familiarize the students with the usage of 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 and variance reduction. Later in the course, the concept of simulation-based optimization and output analysis will be discussed. The example of simulation (and optimization) applied to design an optimal organ allocation policy in the US will be discussed.

In this talk I will report on various research projects that I carried out with my students to better understand the interaction landscape and will report on lessons we learned. I will focus mostly on AR-based setups with application examples from physical flow visualization, molecular visualization, visualization of particle collisions, biomolecular dynamics in cells, and oceanography. I will show interaction techniques that rely on purely gestural interaction, phones or tablets as input and control devices, and hybrid setups that combine traditional workstations with AR views. I will discuss navigation, data selection, and visualization system control as different interaction tasks. With this overview I aim to provide an understanding of typical challenges in immersive visualization environments and how to address some of these challenges.

From my experience, I will try to answer doubts and dilemmas PhD students are often faced with, in their path towards a degree. Namely, I'll discuss how advisors, colleagues, peers, reviewers and so forth, fit in the universe of a PhD student, and I will end sharing my own definition of 'excellence', as an objective to pursue.

Skoltech Applied AI center’s mission is to create AI models and frameworks for solving the problems of sustainable development of industry and economy. In my presentation, I will overview the current center's activities, applied and fundamental problem statements, and corresponding recent results.

Reinforcement Learning provides an attractive suite of online learning methods for personalizing interventions in Digital Behavioral Health. However, after a reinforcement learning algorithm has been run in a clinical study, how do we assess whether personalization occurred? We might find users for whom it appears that the algorithm has indeed learned in which contexts the user is more responsive to a particular intervention. But could this have happened completely by chance? We discuss some first approaches to addressing these questions.

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.