Events

Apr 16 - Apr 22, 2023

• 

  Serverless Computing: With Great Freedom Comes Great Opportunity!

  Marco Canini, Associate Professor, Computer Science

  Apr 17, 12:00 - 13:00

  B9 L2 H2 H2

  serverless computing

  This talk introduces serverless computing, a programming model that has flourished in the last few years, mainly because it allows developers to concentrate on the application logic and not worry about scalability and resource management. Current serverless offerings give users limited flexibility for configuring the resources allocated to their function invocations. We take a principled approach to the problem of resource allocation for serverless functions, analyzing the effects of automating this choice in a way that leads to the best combination of performance and cost.

Apr 9 - Apr 15, 2023

• 

  A personal path from mathematics to biomedical research

  Apr 12, 12:00 - 13:00

  B2 L5 R5209

  Biomedical Computational biology

  A personal presentation describing the role of computational biology and bioinformatics in addressing state-of-the-art biomedical challenges. First, I will provide an overview of the transition between a Ph.D. in Mathematics to a postdoc in Computational Biology: How did it happen? What were the challenges? Secondly, I will briefly present several current case studies where computational biology (in several flavors) is core to understanding novel biological data related to multi-omic data analysis, spatial profiling, gene therapy, and more.
• 

  Web-based 3D Visualization

  Ivan Viola, Professor, Computer Science

  Apr 10, 12:00 - 13:00

  B9 L2 H2 H2

  nanovisualization computer graphics 3D graphics WebGPU WebAssmbly

  In this seminar I will present how to create 3D computer graphics and visualization systems for the web, using WebAssmbly and WebGPU language specifications, which are new, bleeding-edge technologies. Previously, accelerated graphics on the web was based on JavaScript libraries, which is still very popular, but they do not offer detailed memory management and code optimization, necessary for systems requiring high memory load and high computational demands. WebAssembly and WebGPU can be compiled from the C++ or Rust code, which also allows the deployment of the same codebase either for web or for the desktop-based applications.

Apr 2 - Apr 8, 2023

• 

  Cybersecurity of Industrial Control Systems - Challenges and Research Directions

  Awais Rashid, Professor of Cybersecurity, the University of Bristol, Director of the EPSRC Centre for Doctoral Training in Trust, Identity, Privacy and Security in Large-Scale Infrastructures

  Apr 3, 12:00 - 13:00

  B9 L2 H2 H2.

  cybersecurity industrial control systems

  This Distinguished Lecture is part of the CS Graduate Seminars. Abstract Industrial Control Systems play an important role in monitoring, controlling, and automating critical infrastructure such as water, gas, oil, and electricity. Recent years have seen a number of high-profile cyber attacks on such infrastructure, exemplified by Triton, Colonial Pipeline, and the Ukrainian Power Grid attacks. This naturally begs the question: how should we manage cyber security risks in such infrastructure on which the day-to-day functioning of our society relies? What are the complexities of managing

Mar 26 - Apr 1, 2023

• 

  End-to-Same-End Encryption: Modularly Augmenting an App with an Efficient, Portable, and Blind Cloud Storage

  Qiang Tang, Senior Lecturer (equal to U.S. Associate Professor), the University of Sydney

  Mar 30, 12:00 - 13:00

  B4 L5 R5220.

  cloud storage End-to-Same-End-Encryption

  Cloud storage is pervasive nowadays; surprisingly, how to secure cloud storage that is usable in the real world is in fact still open. In this work, we propose a novel system called End-to-Same-End Encryption (E2SEE) that can be deployed directly on existing infrastructure and provide both security and usability. Our system can be flexibly used to augment any App with secure storage, for users to create a personal digital lockbox, and for the cloud to provide secure storage service. A preliminary version of E2SEE was deployed in Snapchat, serving hundreds of millions of users, and the research result was published at USENIX Security 22.
• 

  Challenges in ML for Sustainable Development

  Prof. Laure Berti, Computer Science, Research Director, French Institute of Research for Sustainable Development (IRD)

  Mar 28, 14:00 - 15:00

  B1 L4 R4214

  data cleaning and preparation data fusion

  This talk will present recent approaches for mitigation and adaptation, for which data analytics and ML are parts of the solution in a larger context of interdisciplinary and methodological research and innovations.
• 

  Thoughts on software and systems engineering - 2023-03-27

  Eric Feron, Professor, Electrical and Computer Engineering

  Mar 27, 12:00 - 13:00

  B9 L2 H2 H2

  Complex systems and software engineering, and associated challenges become increasingly important for the well-being and safety of our society of humans. Motivated by this push towards ever more complex systems and software of all sizes, spectacular failures, and decades of questioning in a variety of contexts and endeavors, this talk presents a theory of complex systems engineering, that is, a scientific theory in which an engineered system or software can be seen as a validated scientific hypothesis arising from a convergent mix of mathematical and validated experimental constructs. In its simplest form, a complex engineered system is a manufactured, validated scientific hypothesis arising from a mathematical theorem similar to those found in theoretical physics. This observation provides suggestions for improving system design, especially system architecture, by leveraging advanced mathematical and / or scientific concepts. In return, mathematicians and computer scientists can benefit from this bridge to engineering by bringing to bear many of their automated and manual theorem proving techniques to help with the design of complex systems.

Mar 19 - Mar 25, 2023

• 

  Making federated learning practical and confidential

  Dr. Ruichuan Chen, Distinguished Member of Technical Staff and a Tech Lead, Nokia Bell Labs

  Mar 23, 15:30 - 16:30

  B4 L5 R5209

  Federated learning

  Federated learning (FL) is increasingly deployed among multiple clients to train a shared model over decentralized data. To address the privacy concerns, FL systems need to protect the clients' data from being revealed during training, and also control data leakage through trained models when exposed to untrusted domains. However, existing FL systems (with distributed differential privacy) work impractically in the presence of client dropout, resulting in either poor privacy guarantees or degraded training accuracy. In addition, existing FL systems focus on safeguarding the privacy of training data, but not on protecting the confidentiality of the models being trained, which are increasingly of high business value. In this talk, I will present two pieces of our recent work that aim to address these aforementioned issues.
• 

  Interpretation, Verification and Privacy Techniques for Improving the Trustworthiness of Neural Networks

  Arnaud Dethise, Ph.D. Student, Computer Science

  Mar 22, 12:30 - 14:30

  B1 L3 R3119

  This presentation addresses the challenges associated with trusting Neural Networks due to their black-box nature and limited ability to answer important questions on how they behave. The thesis proposes techniques that increase the trustworthiness of Neural Network models by employing approaches to overcome their black-box nature. The techniques include efficient extraction and verification of weights and decisions to ensure correctness with regards to pre-existing properties, continuous and exact explanations of the model behavior, and scalable training techniques providing strong, theoretically provable guarantees of privacy. We provide strong, approximation-free guarantees about Neural Networks, improving their trustworthiness to make it more likely that users will be willing to deploy them in the real world.
• 

  Tackling credential abuse together

  Michael Reiter, James B. Duke Distinguished Professor, Departments of Computer Science and Electrical & Computer Engineering, Duke University

  Mar 20, 12:00 - 13:00

  B9 L2 H2 H2.

  data security

  Despite long-ago predictions (e.g., see Bill Gates, 2004) that other user-authentication technologies would replace passwords, passwords remain not only pervasive but have flourished as the dominant form of account protection, especially at websites such as retailers that require a low-friction user experience. This talk will describe our research on methods to tackle three key ingredients of account takeovers for password-protected accounts today: (i) site database breaches, which is the largest source of stolen passwords for internet sites; (ii) the tendency of users to reuse the same or similar passwords across sites; and (iii) credential stuffing, in which attackers submit breached credentials for one site in login attempts for the same users' accounts at another.

Mar 12 - Mar 18, 2023

• 

  Robust Geometry Processing for Physical Simulation

  Prof.Daniele Panozzo

  Mar 13, 15:45 - 16:45

  B4 L5 R5209

  geometry processing physical simulation

  I will discuss the limitations of the current state of the art, and present a proposal for an integrated pipeline, considering data acquisition, meshing, basis design, and numerical optimization as a single challenge, where tradeoffs can be made between different phases to increase automation and efficiency. I will demonstrate that this integrated approach offers many advantages, while opening exciting new geometry processing challenges, and that a fully opaque meshing and analysis solution is already possible for heat transfer and elasticity problems with contact. I will present a set of applications enabled by this approach in reinforcement learning for robotics, force measurements in biology, shape design in mechanical engineering, stress estimation in biomechanics, and simulation of deformable objects in graphics.
• 

  Inter-Surface Maps

  Prof.Leif Kobbelt

  Mar 13, 14:30 - 15:30

  B4 L5 R5209

  inter-surface maps 3D shapes

  Many tasks in the analysis and synthesis of (collections of) 3D shapes boils down to computing a map between two surfaces. Such inter-surface maps can be used to establish correspondences, to transfer information or annotation from one object to another, or to plausibly deform one shape into another. If the two shapes are represented as polygon meshes, a continuous inter-surface map does not only assign the vertices of the source mesh to the target mesh but also maps the interior of the triangles which adds to the complexity of the task.
• 

  Discrete Surfaces from Developable Strips

  Prof.Christian Müller

  Mar 13, 13:30 - 14:30

  B4 L5 R5209

  Geometry geometry processing developable strips

  We will discuss several settings in which smooth developable strips are attached to each other or assembled in some other way to obtain surfaces with interesting geometric properties. Driven by the view towards applications we will investigate collections of strips which lie orthogonal or tangential to a reference surface and assume particular shapes. Such strips can serve as support structures or cladding panels of free-form shapes in architectural contexts. Our focus will lie on surfaces with a constant ratio of principal curvatures, cone nets, geodesic grid shells, and others.
• 

  Computing in the Specialization Era

  Prof.Gustavo Alonso, Computer Science, ETH Zurich

  Mar 13, 12:00 - 13:00

  B9 L2 H2 H2

  cloud computing FPGA Hardware acceleration

  In this talk I will discuss the shift towards hardware acceleration and show with several examples from industry and from research the large role that FPGAs are playing. I will hypothesize that we are in a new era where most of the established assumptions, rules of thumb, and accumulated wisdom about many aspects of computation in general and of data processing in particular no longer hold and need to be revisited.
• 

  Cohomology in fluids

  Prof.Albert Chern

  Mar 13, 11:15 - 12:15

  B4 L5 R5209

  fluids cohomology fluid dynamics Geometry geometry processing

  We present a topological analysis of the vorticity formulation in describing fluid dynamics. Despite its widespread use in fluid mechanics, this formulation is insufficient at describing fluid dynamics on a non-simply-connected domain. What is missing is an equation of motion for fluid's cohomology component, which exhibits fascinating dynamics previously under explored. Using geometric language, we derive the new equation of motion and establish new conservation laws, as Casimir invariants in Hamiltonian mechanics, for fluids on domains with general topology. Significantly, we present the first physically correct vortex method on curved surfaces with genus and boundaries.
• 

  Discrete Laplacians for Polygons and Polyhedral

  Prof.Mario Botsch

  Mar 13, 10:15 - 11:15

  B4 L5 R5209

  discrete laplacians polygons polyhedra computer graphics

  Being able to accurately solve PDEs on arbitrary polygonal/polyhedral meshes is a central goal and has been considered for various differential operators over the last years. In this talk I will present a simple approach for computing (piecewise) linear and quadratic basis functions for general polygons and polyhedra, from which discrete operators for gradient, divergence and Laplacian can be derived.
• 

  5-axis flank CNC machining of free-form surfaces using custom-shaped tools

  Dr.Michael Barton

  Mar 13, 09:00 - 10:00

  B4 L5 R5209

  free-form surfaces geometric computing

  In this talk, I will discuss our recent advances in approximation of free-form surfaces by motions of curvature varying tools in the context of 5-axis flank CNC machining. In particular, I will discuss path-planning strategies using fixed tools, or custom-shaped ones, and on an example of spiral bevel gears will demonstrate even more efficient variant of flank machining, called double-flank.
• 

  Workshop on Applied Geometry and Visual Computing

  Mar 13, 08:55 - 17:00

  B4 L5 R5209

  applied geometry visual computing discrete differential geometry geometry processing

  The “KAUST Workshop on Applied Geometry and Visual Computing” brings together leading scientists from Europe and the United States, presenting their latest results in - Applied and Discrete Differential Geometry - Geometry Processing - Computational Fabrication The talks are related to various problems in Applied Mathematics in general and to further areas of Visual Computing such as Computer Graphics, Physical Simulation and Scientific Visualization. The workshop provides a great opportunity to learn about latest developments and to discuss ongoing work with top researchers in the field.

Mar 5 - Mar 11, 2023

• 

  An Overview of Systems Research at TU Munich

  Pramod Bhatotia, Chair Professor, Department of Computer Science, the Technical University of Munich (TUM), Germany.

  Mar 9, 15:30 - 16:30

  B4 L5 R5209

  distributed systems operating systems

  In this talk, Professor Pramod Bhatotia will give an overview of systems research at TU Munich. He will cover his teaching and ongoing research projects. And will conclude the talk with a brief overview of his ERC project.
• 

  A Data Science Pipeline for Big Linked Earth Observation Data

  Prof.Manolis Koubarakis, Informatics and Telecommunications, National and Kapodistrian University of Athens

  Mar 6, 12:00 - 13:00

  B9 L2 H2 H2

  pipeline Geospatial Data GeoSPARQL

  I will present a data science pipeline which starts with Earth observation data arriving in the ground segment of a satellite mission and ends with a complete user application. I will first briefly present all the tools my group has been developing since 2010 for supporting the various stages of the pipeline. Then, I will concentrate on the recently developed system Strabo 2 which can store big geospatial data encoded in RDF and query them using the Open Geospatial Consortium standard GeoSPARQL. Strabo 2 is the only parallel and distributed RDF store available today that can manage terabytes of geospatial data efficiently.

Feb 26 - Mar 4, 2023

• 

  Controlling acoustic wave propagation via rotational motion

  Ying Wu, Professor, Applied Mathematics and Computational Sciences

  Feb 27, 12:00 - 13:00

  B9 L2 H2 H2

  acoustic waves

  Propagation of acoustic waves in time-varying and/or moving media has attracted a lot of attentions and is expected to lead to many intriguing applications. In this talk, I will discuss our recent work on acoustic wave propagation in spinning media (air or water). I will start with a review of the theoretical foundation built upon the Mie scattering framework, in which both the wave equation and the boundary conditions will be specifically discussed. The study is limited in the linear regime and exhibit the peculiar scattering features.
• 

  Learned Optics — Improving Computational Imaging Systems through Deep Learning and Optimization

  Wolfgang Heidrich, Professor, Computer Science

  Feb 26, 12:00 - 13:00

  B9 L2 H2

  Learned Optics

  Computational imaging systems are based on the joint design of optics and associated image reconstruction algorithms.

Feb 19 - Feb 25, 2023

• 

  Visualization Methods for Graphs&Networks

  Prof.Oliver Deussen, Visual Computing, University of Konstanz

  Feb 20, 12:00 - 13:00

  B9 L2 H2 H2

  visualization force-directed layouts stress-based methods vector-based constraints

  Inevitably, the projection of most graph structures on two-dimensional screens will create errors and therefore visually wrong impressions. In the past, two types of methods have been developed to minimize projection errors and distribute them in a visually pleasing way. The first group of methods, force-directed layouts, interpret the links of a graph as physical springs, while stress-based methods minimize an energy function, which aims to map graph distances faithfully.

Feb 12 - Feb 18, 2023

• 

  Generative Models for Neural Fields

  Ivan Skorokhodov, Ph.D. Student, Computer Science

  Feb 15, 20:10 - 22:00

  B1 L2 R2202

  Deep generative models

  In computer vision, generative AI models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this thesis, we develop generative models for images, videos, and 3D scenes which treat the underlying data in such a form and explore the benefits which such a perspective provides.
• 

  Extracting Semantic and Geometric Information in Images and Videos using GANs

  Rameen Abdal, Ph.D. Student, Computer Science

  Feb 15, 18:00 - 20:00

  B1 L2 R2202

  GaN

  The success of Generative Adversarial Networks (GANs) has resulted in unprecedented quality both for image generation and manipulation. Recent state-of-the-art GANs (e.g., the StyleGAN series) have demonstrated outstanding results in photo-realistic image generation. In this dissertation, we explore the latent space properties, including image manipulation, extraction of 3D properties, and performing various weakly supervised and unsupervised downstream tasks using StyleGAN and its derivative architectures.
• 

  Entrepreneurship Explored

  Prof.Bülent Erbilgin and Dr.Lama Hakem, KAUST Entrepreneurship Center

  Feb 13, 12:00 - 13:00

  B9 L2 H2 H2

  entrepreneurship Market marketing

  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.
• 

  Designing, Synthesizing, and Automating Domain-Specific Accelerators

  Jian Weng, PhD student, Computer Science Department, UCLA

  Feb 12, 08:30 - 09:30

  KAUST

  Digital signal processing

  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.

Feb 5 - Feb 11, 2023

• 

  Vulnerability discovery in binaries and protocols

  Prof. Sven Dietrich, the Computer Science Department, Hunter College, the City University of New York (CUNY)

  Feb 9, 15:30 - 16:30

  B5 L5 R5209

  software

  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.
• 

  Point processes and their application to modeling drug seizure and overdose interactions

  Prof. George Mohler, Computer Science, Boston College

  Feb 8, 17:00 - 18:00

  KAUST

  point processes stochastic models

  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-assisted Quality of Transmission Estimation in Optical Networks

  Andrea Bianco, Full Professor, Electronics and Telecommunications Department at Politecnico di Torino

  Feb 8, 13:00 - 14:00

  B9 L4 R4125

  machine learning explainable AI framework artificial intelligence

  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.
• 

  EF21-P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression

  Feb 6, 12:00 - 13:00

  B9 L2 H2 H2

  EF21-P distributed optimization gradient descent operation

  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.

Jan 29 - Feb 4, 2023

• 

  Fighting against cyber threats from a system perspective

  Prof. David Bromberg, Distributed computing systems, University of Rennes (IRISA)

  Feb 2, 15:30 - 16:30

  B4 L5 R5220.

  cyber threats

  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
• 

  Prototypical Random Walk Learning Mechanisms for Few-shot Learning, Novel Visual Generation, and (Continual)? Zero-shot Recognition

  Mohamed Elhoseiny, Associate Professor, Computer Science

  Jan 30, 12:00 - 13:00

  B9 L2 H2 H2

  prototypical random walks zero-shot recognition

  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.

Jan 22 - Jan 28, 2023

• 

  Securing data against non-conventional adversaries

  Prof. Mohammad Mannan, Concordia Institute for Information Systems Engineering, Concordia University, Montreal

  Jan 26, 15:30 - 16:30

  B4 L5 R5220.

  data security

  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.
• 

  Towards Richer Video Representation for Action Understanding

  Humam Alwassel, Ph.D. Student, Computer Science

  Jan 23, 18:30 - 20:30

  B2 L5 R5209

  Computer Vision machine learning Human Activity Recognition

  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.
• 

  Principles and practice of TEE replication (and beyond)

  Prof.Rodrigo Rodrigues, Instituto Superior Tecnico (ULisboa)

  Jan 23, 12:00 - 13:00

  B9 L2 R2322 H1

  TEE replication TEEMS CFT replication protocol

  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.

Dec 4 - Dec 10, 2022

• 

  Reynolds-robust preconditioners for the stationary incompressible Navier--Stokes equations

  Prof.Patrick Farrell, University of Oxford

  Dec 5, 12:00 - 13:00

  B9 L2 R2322 H1

  Navier-Stokes equation Robustness

  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.

Nov 27 - Dec 3, 2022

• 

  Bridging the Gap between the Academia and Industry by Extending High-Quality Research to Practical Business Needs

  Dr.Syed Adnan Yusuf

  Nov 28, 12:00 - 13:00

  B9 L2 R2322 H1

  Computer Vision robotics automation IoT nlp artificial intelligence

  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.

Nov 20 - Nov 26, 2022

• 

  On training algorithms for neural networks

  Jinchao Xu, Professor, Applied Mathematics and Computational Sciences

  Nov 21, 12:00 - 13:00

  B9 L2 R2322 H1

  Deep learning deep neural networks

  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

Nov 13 - Nov 19, 2022

• 

  Parameter-Free Online Optimization: Past, Present, and Future

  Francesco Orabona, Associate Professor of Electrical and Computer Engineering, Boston University

  Nov 14, 12:00 - 13:00

  B9 L2 R2322

  Parameter-free online optimization machine learning

  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.

Nov 6 - Nov 12, 2022

• 

  Introduction to Computer Simulation - A short course II - Part 3

  Prof. Michal Mankowski, Assistant Professor of Operations Research, Erasmus University Rotterdam, Netherlands

  Nov 10, 10:00 - 11:30

  B1 L3 R3119

  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.
• 

  Introduction to Computer Simulation - A short course II - Part 2

  Prof. Michal Mankowski, Assistant Professor of Operations Research, Erasmus University Rotterdam, Netherlands

  Nov 9, 10:00 - 11:30

  B1 L3 R3119

  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.
• 

  Introduction to Computer Simulation - A short course II - Part 1

  Prof. Michal Mankowski, Assistant Professor of Operations Research, Erasmus University Rotterdam, Netherlands

  Nov 8, 10:00 - 11:30

  B1 L3 R3119

  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.
• 

  Thoughts on how to Effectively Explore Visual Representations in Mixed Reality

  Tobias Isenberg, Senior Research Scientist, Inria

  Nov 7, 12:00 - 13:00

  B9 L2 R2322 H1

  virtual reality data visualisation Scientific Visualization

  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.

Oct 30 - Nov 5, 2022

• 

  Everything PhD students always wanted to know about research* (*but were afraid to ask)

  Oct 31, 12:00 - 13:00

  B9 L2 R2322 H1

  scientific research PhD student

  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.

Oct 23 - Oct 29, 2022

• 

  Applied AI for sustainable development

  Prof.Evgeny Burnaev, Applied AI Center, Skolkovo Institute of Science and Technology

  Oct 24, 12:00 - 13:00

  B9 L2 R2322 H1

  Skoltech machine learning Bayesian modeling artificial intelligence

  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.

Oct 16 - Oct 22, 2022

• 

  Inference for Longitudinal Data After Adaptive Sampling

  Prof. Susan Murphy, Statistics and Computer Science and Radcliffe Alumnae Professor at the Radcliffe Institute, Harvard University

  Oct 20, 15:00 - 16:00

  B9 L2 H2

  Reinforcement Learning

  In this work, we proved statistical inference for the common Z-estimator based on adaptively sampled data. Adaptive sampling methods, such as reinforcement learning (RL) and bandit algorithms, are increasingly used for the real-time personalization of interventions in digital applications like mobile health and education. As a result, there is a need to be able to use the resulting adaptively collected user data to address a variety of inferential questions, including questions about time-varying causal effects.
• 

  We used Reinforcement Learning; but did it work?

  Prof. Susan Murphy, Statistics and Computer Science and Radcliffe Alumnae Professor at the Radcliffe Institute, Harvard University

  Oct 19, 16:00 - 17:00

  B9 L2 H2

  Reinforcement Learning Digital Behavioral Health

  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.

Oct 9 - Oct 15, 2022

• 

  EF-BV: distributed optimization with compressed communication

  Laurent Condat, Senior Research Scientist, Computer, Electrical and Mathematical Sciences and Engineering

  Oct 10, 12:00 - 13:00

  B9 L2 R2322 H1

  big data distributed computing Federated learning

  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.

Oct 2 - Oct 8, 2022

• 

  Towards Structured Intelligence with Deep Graph Neural Networks

  Guohao Li, Ph.D. Student, Computer Science

  Oct 5, 18:00 - 20:00

  B5 L5 R5209

  graph machine learning Graph Neural Networks

  This dissertation discusses approaches to building large-scale and efficient graph machine learning models for learning structured representation with applications to engineering and sciences. This work would present how to make Graph Neural Networks (GNNs) go deep by introducing architectural designs and how to automatically search GNN architectures by novel neural architecture search algorithms.