optimization

Chengjie zhao

Chengjie Zhao

Visiting Researcher, Information Science Lab
Visiting Student, King Abdullah University of Science and Technology

Chaabane Mankai

Surrounded by bright minds and groundbreaking research, KAUST is a great place to learn and grow.

Conformal Mapping and Invariants – Motivating Numerical PDE Approaches

-

B1 L3 R3119

This study explores conformal mappings and invariants, particularly capacity and hyperbolic length, using PDE-based numerical methods (hp-FEM and BIE) to solve geometric optimization problems, such as minimizing heat loss or maximizing it under distance constraints, for domains with complex geometries.

Convergence of Descent Methods under Polyak- Lojasiewicz-Kurdyka Properties

-

B1 L3 R3119

This talk presents a novel convergence analysis for a class of descent methods in nonsmooth and nonconvex optimization under the Polyak-Lojasiewicz-Kurdyka properties, proving finite termination under certain conditions and revealing incompatibilities between these properties and gradient Lipschitz continuity in certain frameworks.

Ahmed Youssef Ragab Radwan

Visiting Student (former), Information Science Lab
Visiting student at the Information Science Lab, in the Electrical Engineering Department, CEMSE, King Abdullah University of Science and Technology (KAUST)

KAUST Research Workshop on Optimization and Big Data

-

B19 L3 H2

The age of "big data" is here: data of unprecedented sizes is becoming ubiquitous, which brings new challenges and new opportunities. With this comes the need to solve optimization problems of unprecedented sizes.

Everything you always wanted to know about single machine large-scale graph analytics

-

B9 L2 H1

Abstract: Graphs are a natural way to capture relations among objects or people. This has led to graph processing systems being used in a wide variety of fields, ranging from biology to social networks, and a large number of such systems have been described in the recent literature. The focus of our recent work is on single machine graph processing systems where the graph is processed from main memory or external storage. We perform a systematic comparison of various techniques proposed to speed up in-memory multicore graph processing. In addition, we take an end- to-end view of execution time

Estimating the expected information gain in Bayesian optimal experimental design

-

B9 L2 H1

Optimal experimental design for parameter estimation is a fast-growing area of research. Let us consider the experimental goal to be the inference of some attributes of a complex system using measurement data of some chosen system responses, and the optimal designs are those that maximize the value of measurement data. The value of data is quantified by the expected information gain utility, which measures the informativeness of an experiment. Often, a mathematical model is used that approximates the relationship between the system responses and the model parameters acting as proxies for the attributes of interest.

Spectrum Management for Future Generations of Cellular Networks

-

B1 L2 R2202

The demand for wireless communication is ceaselessly increasing in terms of the number of subscribers and services. Future generations of cellular networks are expected to allow not only humans but also machines to be immersively connected. However, the radio frequency spectrum is already fully allocated. Therefore, developing techniques to increase spectrum efficiency has become necessary. In that context, this dissertation analyzes two spectrum sharing techniques that enable efficient utilization of the available radio resources in cellular networks. The first technique, called full-duplex (FD) communication, uses the same spectrum to transmit and receive simultaneously. The second spectrum sharing technique, called non-orthogonal multiple access (NOMA), allows a transmitter to communicate with multiple receivers through the same frequency-time resource unit.

Virtual sensing: methods and applications

-

B9 L2 H1 R2322

Abstract Due to the inherent complexity, physical or economical constraints, a number of important physical and biological systems are inaccessible. Only few, often indirect, experimental data are available to extract information or to manipulate and control the system. Introduced as a promising technology to respond to the growing need for reliable, accurate, fast, robust and low-cost sensing strategies, virtual sensors are gaining importance in several fields. These sensors combine the available data with effective estimation methods and algorithms to access non-measurable variables of

Use Mathematics and get a SPARQL Query Engine (almost) for Free! It’s MAGiQ!

-

B9 L2 H1 R2322

Existing RDF engines are designed for specific hardware architectures; porting to a different architecture (e.g., GPUs) entails enormous implementation effort. We explore sparse matrix algebra as an alternative for designing a portable, scalable and efficient RDF engine.

Langevin Monte Carlo as an optimization algorithm

-

B9 L2 H1 R2322

Adil Salim is mainly interested in stochastic approximation, optimization, and machine learning. He is currently a Postdoctoral Research Fellow working with Professor Peter Richtarik at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST).

Dynamics and Convergence of Weight Normalization for Training Neural Networks

Guido Montufar, Assistant Professor, Departments of Mathematics and Statistics, University of California, Los Angeles (UCLA)

-

B1 L3 R3119

We present a result on the convergence of weight normalized training of artificial neural networks. In the analysis, we consider over-parameterized 2-layer networks with rectified linear units (ReLUs) initialized at random and trained with batch gradient descent and a fixed step size. The proof builds on recent theoretical works that bound the trajectory of parameters from their initialization and monitor the network predictions via the evolution of a ''neural tangent kernel'' (Jacot et al. 2018). We discover that training with weight normalization decomposes such a kernel via the so called ''length-direction decoupling''. This in turn leads to two convergence regimes. From the modified convergence we make a few curious observations including a natural form of ''lazy training'' where the direction of each weight vector remains stationary.

Space-Time Tomographic Reconstruction of Deforming Objects

-

B1 L2 R2202

In this thesis, a variety of applications in computer vision and graphics of inverse problems using tomographic imaging modalities will be presented: (i) The first application focuses on the CT reconstruction with a specific emphasis on recovering thin 1D and 2D manifolds embedded in 3D volumes. (ii) The second application is about space-time tomography (iii) Base on the second application, the third one is aiming to improve the tomographic reconstruction of time-varying geometries undergoing faster, non-periodic deformations, by a warp-and-project strategy. Finally, with a physically plausible divergence-free prior for motion estimation, as well as a novel view synthesis technique, we present applications to dynamic fluid imaging which further demonstrates the flexibility of our optimization frameworks

Understanding a Block of Layers in Deep Neural Networks: Optimization, Probabilistic and Tropical Geometric Perspectives

-

KAUST

In this dissertation, we aim at theoretically studying and analyzing deep learning models. Since deep models substantially vary in their shapes and sizes, in this dissertation, we restrict our work to a single fundamental block of layers that is common in almost all architectures. The block of layers of interest is the composition of an affine layer followed by a nonlinear activation function and then lastly followed by another affine layer. We study this block of layers from three different perspectives. (i) An Optimization Perspective. We try addressing the following question: Is it possible that the output of the forward pass through the block of layers highlighted above is an optimal solution to a certain convex optimization problem? As a result, we show an equivalency between the forward pass through this block of layers and a single iteration of certain types of deterministic and stochastic algorithms solving a particular class of tensor formulated convex optimization problems.

Quantitative understanding of transcription factor regulation at network- and molecular-levels through optimization and deep learning

-

KAUST

Transcription factors are an important family of proteins that control the transcription rate from DNAs to messenger RNAs through the binding to specific DNA sequences. Transcription factor regulation is thus fundamental to understanding not only the system-level behaviors of gene regulatory networks, but also the molecular mechanisms underpinning endogenous gene regulation. In this talk, I will introduce our efforts on developing novel optimization and deep learning methods to quantitatively understanding transcription factor regulation at network- and molecular-levels. Specifically, I will talk about how we estimate the kinetic parameters from sparse time-series readout of gene circuit models, and how we model the relationship between the transcription factor binding sites and their binding affinities.

Trajectory Planning for Autonomous Underwater Vehicles: A Stochastic Optimization Approach

-

KAUST

In this work, we develop a new framework of trajectory planning for AUVs in realistic ocean scenarios. We divide this work into three parts. In the first part, we provide a new approach for deterministic trajectory planning in steady current, described using Ocean General Circulation Model (OGCM) data. The latter are used to specify both the ocean current and the bathymetry. We apply a NLP to the optimal-time trajectory planning problem. To demonstrate the effectivity of the resulting model, we consider the optimal time trajectory planning of an AUV operating in the Red Sea and the Gulf of Aden. In the second part, we generalize our 3D trajectory planning framework to time-dependent ocean currents. We also extend the framework to accommodate multi-objective criteria, focusing specifically on the Pareto front curve between time and energy. The scheme is demonstrated for time-energy trajectory planning problems in the Gulf of Aden. In the last part, we address uncertainty in the ocean current field. The uncertainty in the current is described in terms of a finite ensemble of flow realizations. The proposed approach is based on a non-linear stochastic programming methodology that uses a risk-aware objective function, accounting for the full variability of the flow ensemble. Advanced visualization tools are used to amplify simulation results.

Stochastic Optimization in Target Positioning and Location-based Applications

-

KAUST

This event has been postponed from 20th July to 27th July. Stochastic optimization refers to the minimization/maximization of an objective function in the presence of randomness. The randomness may appear in objective functions, constraints, or optimization methods. It has the advantage of dealing with uncertainties that deterministic optimizers cannot solve or cannot solve efficiently. In this work, we discuss the implementation of stochastic optimization methods in solving target positioning problems and tackling key issues in location-based applications.

Optimal Algorithms for Affinely Constrained, Distributed, Decentralized, Minimax, and High-Order Optimization Problems

-

B5 R5220

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.

Powering the bottom line

1 min read ·
A risk-based optimization scheme boosts confidence and profitability for future mixed-technology power plants.

Aerial Path Planning for Urban Scene Reconstruction: A Continuous Optimization Method and Benchmark

1 min read ·
Small unmanned aerial vehicles (UAVs) are ideal capturing devices for high-resolution urban 3D reconstructions using multi-view stereo. Nevertheless, practical considerations such as safety usually mean that access to the scan target is often only available for a short amount of time, especially in urban environments. It, therefore, becomes crucial to perform both view and path planning to minimize flight time while ensuring complete and accurate reconstructions. In this work, we address the challenge of automatic view and path planning for UAV-based aerial imaging with the goal of urban

Adel is invited to give a talk in EECVC on "Optimization meets Deep Learning"

1 min read ·
​Adel is invited to give a talk in EECVC on "Optimization meets Deep Learning"​. It is a 45 minutes talk scheduled on the 6th of July 2019.

Accelerating the grapevine effect

1 min read ·
By looking at classical gossip algorithms from a novel perspective, KAUST Professor Peter Richtarik has found a way to significantly speed up gossip-based information sharing, and in the process, he discovered new applications for this efficient mathematical approach. Gossip involves the sharing of information between individuals in a network and can be applied mathematically in both human social networks and data networks, such as distributed sensors. “A network is a collection of nodes, each connected to other nodes via links,” explains Richtarik. “In social networks, for instance

KAUST Professor Peter Richtárik wins Distinguished Speaker Award

1 min read ·
Peter Richtárik, KAUST professor of computer science, recently received a Distinguished Speaker Award at the Sixth International Conference on Continuous Optimization (ICCOPT 2019) held in Berlin from August 3 to 8. ICCOPT 2019 was organized by the Mathematical Optimization Society and was hosted this year by the Weierstrass Institute for Applied Analysis and Stochastics.

An Airline observatory created by Passengers for Passengers

1 min read ·
The COVID-19 pandemic has generated a significant worldwide disruption to flight operations, affecting the lives of millions of passengers.

Meet KAUST Prospective Student: Igor Sokolov

1 min read ·
Igor Sokolov, 23, is an applied mathematics and physics graduate who will join KAUST from the Moscow Institute of Physics and Technology, Russia. Igor first came to KAUST as a visiting student in 2019 and was highly impressed by the University's living and working facilities. It was this first impression that prompted him to pursue an M.S. at KAUST. Sokolov will join KAUST in the Fall of 2020 as an M.S. candidate under the supervision of Professor Peter Richtarik.

Meet KAUST student: Grigory Malinovsky

1 min read ·
Grigory Malinovsky joined KAUST this fall as a M.S./Ph.D. candidate and member of Professor Peter Richtarik's Optimization and Machine Learning Lab. Grigory holds a bachelor's degree in applied mathematics and physics from the Moscow Institute of Physics and Technology, Russia. Malinovsky first came to KAUST as a visiting student and was instantly impressed by the research facilities and working atmosphere. His outstanding internship experience was a catalyst in choosing KAUST as the next step in his academic career.

Yongliang Yang

Research Scientist, Computer Science
Yongliang Yang was a Research Scientist at the Visual Computing Center in King Abdullah University of Science and Technology (KAUST). Currently, he’s an Assistant Professor in Department of Computer Science at University of Bath in United Kingdom. Education and Early Career Yongliang received his Bachelor degree in Computer Science and Technology in 2004, from Tsinghua University. He continued to pursue his Master and Ph.D. degree in Graphics and Geometric Computing Group in Tsinghua, under the supervision of Prof. Shi-Min Hu. In 2009, he joined KAUST as a Postdoctoral Fellow working with Prof

Tariq Alturkestani

Ph.D. Student, Computer Science
Tariq is a PhD student in Computer Science working under the supervision of Professor David E. Keyes. He is working on developing a library that enables users to overlap I/O and compute. Tariq holds a Bachelors degree from Penn State University and a Master from KAUST. Education Profile MS, Computer Science, King Abdullah University of Science and Technology (KAUST), 2014. BS, Computer Science, Penn State University, USA, 2013.

Samuel Horváth

Ph.D. Student, Statistics
Samuel Horváth is a Ph.D. candidate at Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Peter Richtarik in his research group. Education and Early Career Samuel studied Financial Mathematics at Comenius University in Bratislava, Slovakia and obtained his bachelor in 2017. Then, he joined the MS/PhD program in Statistics and Optimization at KAUST in 2017. In 2018, he had an internship (Machine Learning Intern) at Exponea for 3 months. Research Interest His research interest include Optimization for Big Data

Rolf Krause

Professor Rolf Krause is an experienced researcher and educator specializing in designing and analyzing algorithms to solve complex problems in scientific computing and machine learning.

Ricardo Manuel Pinto de Lima

My mission is to develop computational models and methods based on mathematical optimization and data science for sustainable energy and chemical processes. I am deeply committed to decarbonization, climate change mitigation, and optimal operations management.

Rafal Szlendak

Rafał Szlendak is an MS/PhD student in the AMCS program under the supervision of Prof. Peter Richtarik. His biggest passions are research, weightlifting and travelling. His career path is motivated by his endless passion for self-development and discovery. Education and Early Career Rafał Szlendak has obtained his Bachelor's degree in Mathematics and Statistics from University of Warwick Research Interest In his research Rafał focuses on stochastic gradient descent algorithms for large-scale machine learning problems. His primary goal is developing state-of-the-art methods with sound

Ramzi Idoughi

Research Scientist, Computer Science
Ramzi Idoughi is a Research Scientist in the Computational Imaging Group (VCCIMAGING) working with Professor Wolfgang Heidrich at King Abdullah University of Science and Technology (KAUST). Education and Early Career Ramzi obtained his engineering degree in Space System and Image Processing from National Higher French Institute of Aeronautics and Space (ISAE/SUPAERO) in France in 2011. Later, he received his master degree in Signal, Image, Acoustics and Optimization (SIAO) from Higher Educational Institution in Toulouse (ENSEEIHT) in France in 2011. After that in 2015, he received his doctoral

Qizhou Wang

Qizhou Wang is an M.S./Ph.D. candidate in the KAUST Primalight research group under the supervision of Professor Andrea Fratalocchi. Before joining KAUST, Qizhou obtained a bachelor's degree in communication engineering from the University of Electronic Science and Technology, China. Research Interests Qizhou's research interests include machine learning, optimization theories and computer vision.

Qilin Sun

Qilin Sun is a Ph. D. candidate in the Computational Imaging Group (VCCIMAGING) under the supervision of Professor Wolfgang Heidrich at King Abdullah University of Science and Technology (KAUST). Education and Early Career Qilin Sun obtained his bachelor degree in Optical Information Science and Technology from Huazhong University of Science and Technology in Wuhan, China in 2015. After that, he joined KAUST and received his master degree in Electrical Engineering in 2017.Qilin is a CEO&Founder at Point Spread Technology, China. Research Interest Qilin is interested in Computational

Peter Richtarik

Professor, Computer Science
Professor Richtárik specializes in big data optimization and machine learning. He is known for his work on randomized coordinate descent algorithms, stochastic gradient descent and federated learning.

Mher Safaryan

Mher Safaryan is a Postdoctoral Research Fellow working with Professor Peter Richtarik at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Mher received his Ph.D. in Mathematics from Yerevan State University, Armenia under the supervision of Prof. Grigori Karagulyan. Before joining KAUST, he was a Junior Researcher at the Institute of Mathematics of National Academy of Sciences, Real Analysis Department in Armenia. After that, he joined the Computer, Electrical and Mathematical Sciences and Engineering Division (CEMSE)

Laurent Condat

I am a senior researcher working in optimization, in the group of Prof. Peter Richtárik.

Krishnendu S Tharakan

Visiting Student (former), Electrical and Computer Engineering
Visiting student at King Abdullah University of Science and Technology (KAUST).

Konstantin Mishchenko

Ph.D. Student, Computer Science
Konstantin Mishchenko is a Ph.D. candidate at Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Peter Richtarik in his research group. Education and Early Career Konstantin Mishchenko obtained his bachelor degree in Computer Science and Physics from Moscow Institute of Physics and Technology in 2016. After that in 2017, he received his master degree in Machine Learning MASH from Université Paris Dauphine in Paris, France. Konstantin had many internships during his studies. The most recent was with Amazon in

Kai Yi

Ph.D. candidate working on machine learning optimization, LLMs and federated learning.

Itsikiantsoa Randrianantenaina

Itsikiantsoa Randrianantenaina received the Engineering Diploma degree from the Institut National des Postes et Telecommunications, Rabat, Morocco, in 2013, and the M.S. degree in electrical engineering from the King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia, from June 2015- June 2019, where she earned the Ph.D. degree and Joined NEOM, Saudi Arabia, as a Research Engineer after graduation. Her research interests include full-duplex and NOMA systems, interference management, FogRAN architecture, stochastic geometry, and optimization. Education Profile Ph.D

Igor Sokolov

Igor Sokolov is an M.S. candidate in the KAUST Peter Richtarik Research Group under the supervision of Professor Peter Richtarik. Before joining KAUST, Igor obtained a bachelor's degree in applied mathematics and physics from the Moscow Institute of Physics and Technology, Russia. Research Interests Igor's research interests lie in the intersection of optimization and machine learning. He is interested in both the theoretical analysis of optimization algorithms as well as their practically efficient applications.

Guangming Zang

Research Engineer, Computer Science
Guangming Zang is a research engineer in the Computational Imaging Group (VCCIMAGING) under the supervision of Professor Wolfgang Heidrich at King Abdullah University of Science and Technology (KAUST). Education and Early Career Guangming obtained his bachelor degree in Software Engineering from China University of Geosciences in Wuhan, China in 2013. He received his master degree in Computer Science from University of Chinese Academy of Sciences in China. Before joining KAUST, Guangming was a research assistant (2013 – 2014) at The National Space Science Center at Chinese Academy of Sciences

Grigory Malinovsky

Grigory Malinovsky is a M.S./Ph.D. candidate at the KAUST Optimization and Machine Learning Lab under the supervision of Professor Peter Richtarik. Before joining KAUST, Grigory obtained a bachelor's degree in applied mathematics and physics from the Moscow Institute of Physics and Technology, Russia. Research Interests Grigory's research interests include machine learning, optimization, and applied statistics. Specifically, he is interested in the theoretical aspects of optimization algorithms that can be applied to real machine-learning problems. Education Profile B.A., Major in Applied

Ganesh Sundaramoorthi

Ganesh Sundaramoorthi was an Assistant Professor of Electrical Engineering and jointly Assistant Professor of Applied Mathematics and Computational Science at KAUST starting in 2011. He is currently Principal Research Scientist at United Technologies Research Center in East Hartford, CT, USA, formulating computer vision algorithms for robotic inspection applications. Education and Early Career His PhD is in Electrical and Computer Engineering from the Georgia Institute of Technology in Atlanta, GA, USA in 2008. His PhD developed fundamental shape optimization methods for computer vision that

Filip Hanzely

Filip Hanzely is a recent PhD graduate from the group of Peter Richtarik. His research focuses mostly on various aspects of optimization for machine learning, designing provably efficient algorithms for solving big data problems. Filip is joining Toyota Technological Institute in Chicago (TTIC) as a research assistant professor in December 2020. Education and Early Career Filip Hanzely graduated with honor for his bachelor degree in Economics and Financial Mathematics from Comenius University in Bratislava, Slovakia. Later on in 2017, he received his master in science degree in Mathematics and

Francesco Orabona

Associate Professor, Computer Science
Achieving "parameter-free" machine learning is the primary focus of Professor Francesco Orabona. He is particularly interested in designing superior algorithms to train deep learning models.

El Houcine Bergou

Postdoctoral Research Fellow, ‌InfoCloud
As of January 2019, El Houcine Bergou is a Postdoctoral Research Fellow at Extreme Computing Research Center (ECRC) in King Abdullah University of Science and Technology (KAUST), working with Professor Panagiotis Kalnis in his research group. Prior to this, he spent a year as a Postdoctoral Research Fellow in the Optimization and Machine Learning group of Professor Peter Richtárik. Education and Early Career Dr. Bergou has a PhD degree in numerical methods for least squares problems with application to data assimilation from the National Institute of Posts and Telecommunications (INPT) in

Eric Feron

With 31 years of teaching and research experience, Professor Feron’s work utilizes elementary concepts of control systems, optimization and computer science to address critical issues in modern aerospace engineering and robotics.

Elnur Gasanov

Elnur Gasanov is a master student at Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Peter Richtárik in his research group. Education and Early Career Elnur Gasanov obtained his bachelor degree in Applied Mathematics and Physics from Moscow Institute of Physics and Technology (MIPT) in Moscow, Russia in 2018. Research Interest His research interests are in optimization and machine learning. Education Profile ​B.Sc., Applied Mathematics and Physics, Moscow Institute of Physics and Technology (State

Egor Shulgin

Ph.D. Student, Computer Science
Egor Shulgin is a CS student in the MS/Ph.D. program under the supervision of Professor Peter Richtarik at the Visual Computing Center (VCC) at the King Abdullah University of Science and Technology (KAUST), Saudi Arabia. Education and Early Career Egor obtained his bachelor's degree in Applied Mathematics, Physics, and Computer Science from the Moscow Institute of Physics and Technology (MIPT) in 2019. He first came to KAUST for a research visit in 2019. Later, he joined Prof. Peter Richtarik's group as a MS/Ph.D. student. In 2021 Egor did a research internship with Distributed AI team at the

Ebrahim Al-Safadi

Visiting B.S. Student, Information Science Lab
Internship at King Abdullah University of Science and Technology (KAUST).

Dmitry Kovalev

Ph.D. Student, Computer Science
Education Dmitry obtained a B.S. degree from Moscow Institute of Physics and Technology, Moscow, Russia, in 2018. He is an M.S. in the Computer Science program at the King Abdullah University of Science and Technology as of Fall 2018. Publications Dmitry Kovalev, Samuel Horvath and Peter Richtárik. Don't Jump Through Hoops and Remove Those Loops: SVRG and Katyusha are Better Without the Outer Loop, arXiv preprint arXiv:1901.08689, 2019. Dmitry Kovalev, Peter Richtárik, Eduard Gorbunov, Elnur Gasanov. Stochastic Spectral and Conjugate Descent Methods . Advances in Neural Information Processing

David Ketcheson

Professor Ketcheson is an expert in numerical analysis and computational science, specializing in the study of numerical methods for differential equations and the modeling and analysis of time-dependent nonlinear wave phenomena.

Biao Zhang

Ph.D. Student, Computer Science
Biao Zhang is a Computer Science Ph.D. candidate at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST) under the supervision of Professor Peter Wonka in his research group. Education and Early Career Biao Zhang obtained his bachelor degree in Mathematics and master degree in Applied Mathematics from Xi’an Jiaotong University in China. Research Interest Biao Zhang is mainly interested in machine learning and computer vision. Education Profile M.S., Applied Mathematics, Xi’an Jiaotong University, China B.S., Mathematics, Xi’an Jiaotong University

Avetik Karagulyan

Postdoctoral Research Fellow, Optimization and Machine Learning
Avetik Karagulyan have joined the team of Peter Richtarik at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST) as a Postdoctoral fellow in November 2021. Education and Early Career Avetik Karagulyan has defended his thesis at Center of Research in Economics and Statistics (CREST), Paris in June 2021 entitled as "Sampling with the Langevin Monte-Carlo" under the supervision of professor Arnak Dalalyan. In 2018, he received MSc Mathematics, Vision, Learning (MVA) diploma at ENS Paris-Saclay with highest honors. Avetik Karagulyan graduated from

Alibek Sailanbayev

Alibek Sailanbayev is a Ph.D. candidate in Applied Mathematics and Computational Science at Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST), studying under the supervision of Professor Peter Richtarik in his research group. Education and Early Career Alibek obtained his bachelor degree Applied Mathematics from Nazarbayev University in Kazakhstan. He joined KAUST in Fall 2017 and received his M.S. degree in Applied Mathematics and Computational Sciences in December 2018. He is now pursuing Ph.D. studies. Alibek took a Summer Internship at Loria/Inria

Alyazeed Basyoni

M.S. Student, Computer Science
Alyazeed Basyoni is a CS Master Student under the supervision of Professor Peter Richtarik at the Visual Computing Center (VCC) in King Abdullah University of Science and Technology (KAUST). Education and Early Career Alyazeed joined Carnegie Mellon University in Pittsburgh, Pennsylvania and earned his bachelor degree in Computer Science with minor in Mathematics in 2018. Education Profile B.S., Computer Science, Carnegie Mellon University, USA, 2018

Ali H. AlNasser

M.S. Student, Computer Science
Ali AlNasser is a Masters student in Computer Science. His research interests are scaling deep learning algorithms available now to be used on multicore computers by leveraging the high parallelism in Deep learning. Why KAUST? The abundance of opportunities available in KAUST. Education Profile B.S, Electrical & Computer Engineering, University of Colorado at Boulder. B.S, Applied Mathematics, University of Colorado at Boulder.

Alexandra Aguiar Gomes

Alexandra Aguiar Gomes has been a university educator since 1996. Her area of expertise is optimization, with current interests in the mathematics of decision-making for sustainable development and the mathematics of generative artificial intelligence. Alexandra finds joy in simplifying mathematical concepts, helping her students discover the practicality of mathematics in their fields.

Ahmed Douik

Visiting B.S. Student, Computer, Electrical and Mathematical Sciences and Engineering , Quantitative Researcher at Chicago Trading Company PhD candidate at California Institute of Technology

Adil Salim

Postdoctoral Research Fellow, Computer Science
Adil Salim is a Postdoctoral Research Fellow working with Professor Peter Richtarik at the Visual Computing Center (VCC) at King Abdullah University of Science and Technology (KAUST). Education and Early Career Dr. Salim earned his Master degrees in Data Science and Statistical Engineering from ENSAE ParisTech and in Probability Theory and Stochastic Modeling from Paris XI University in France in 2015. He received his Ph.D. in Machine Learning from Télécom ParisTech in France in 2018. Before joining KAUST, Adil worked in many positions starting from an Auditor for banks and insurance companies

Adel Bibi

Adel Bibi is a postdoctoral research assistant in computer vision and machine learning at the Torr Vision Group working with Professor Philip Torr at the University of Oxford. Prior to that, he received his MSc and PhD degrees from King Abdullah University of Science & Technology (KAUST) where he was part of the Image and Video Understanding Lab (IVUL) advised by Professor Bernard Ghanem. Education and Early Career Adel Bibi has a Bachelor’s Degree in Electrical Engineering from Kuwait University in 2014. He received his Master Degree in Electrical Engineering from King Abdullah University of

Abderrazak Chahid

Abderrazak Chahid is a PhD candidate in Electrical and Computer Engineering department within CEMSE division. He obtained his Bachelor of Science degree in Electrical Engineering and Power Electronics from Sultan Moulay Slimane University in Morocco. He then got a Master degree in Electrical Engineering from the National School of Applied Sciences in Morocco before obtaining a second Master of Science degree in Embedded Systems from Lorraine University in France. Abderrazak is currently working on developing biomedical signal/image processing: MRS water suppression, MRI image denoising. He is