Profiles

Before joining KAUST in 2017, Peter Richtárik obtained a Mgr. in Mathematics ('01) at Comenius University in his native Slovakia. In 2007, he received his Ph.D. in Operations Research from Cornell University, U.S., before joining the University of Edinburgh, U.K., in 2009 as an Assistant Professor at the university's School of Mathematics.

The Professor of Computer Science at KAUST is affiliated with the Visual Computing Center and the Extreme Computing Research Center at KAUST.

A number of honors and awards have been conferred on Dr. Richtárik, including the EUSA Award for Best Research or Dissertation Supervisor (Second Prize), 2016; a Turing Fellow Award from the Alan Turing Institute, 2016; and an EPSRC Fellow in Mathematical Sciences, 2016. Before joining KAUST, he was nominated for the Chancellor’s Rising Star Award from the University of Edinburgh in 2014, the Microsoft Research Faculty Fellowship in 2013, and the Innovative Teaching Award from the University of Edinburgh in 2011 and 2012.

Several of his papers attracted international awards, including the SIAM SIGEST Best Paper Award (joint award with Professor Olivier Fercoq); the IMA Leslie Fox Prize (Second prize: M. Takáč 2013, O. Fercoq 2015 and R. M. Gower 2017); and the INFORMS Computing Society Best Student Paper Award (sole runner-up: M. Takáč). Richtárik is the founder and organizer of the "Optimization and Big Data" workshop series. He has given more than 150 research talks at conferences, workshops and seminars worldwide.

He was an Area Chair for ICML 2019 and a Senior Program Committee Member for IJCAI 2019. He is an Associate Editor of Optimization Methods and Software and a Handling Editor of the Journal of Nonsmooth Analysis and Optimization.

Professor Richtárik’s research interests lie at the intersection of mathematics, computer science, machine learning, optimization, numerical linear algebra, high-performance computing and applied probability.

His recent work on randomized optimization algorithms—such as randomized coordinate descent methods, stochastic gradient descent methods, and their numerous extensions, improvements and variants)—has contributed to the foundations and advancement of big data optimization, randomized numerical linear algebra and machine learning.

I got my PhD in 2006 from Grenoble Inst. of Tech., Grenoble, France. After 2 years as a postdoc in Munich, Germany, I was recruited as a permanent researcher by the CNRS in 2008. I spent 4 years in the GREYC, Caen, and 7 years in GIPSA-Lab, Grenoble. From 2016 to 2019, I was a member of the French National Committee for Scientific Research (CoNRS, Section 7). Since Nov. 2019, I am on leave from the CNRS and a senior researcher at KAUST.

Optimization: deterministic and stochastic algorithms, convex relaxations. Applications to machine learning, signal and image processing

• King Abdullah University of Science and Technology (KAUST) December 2021 - Present

PhD in Applied Mathematics and Computational Sciences Thuwal, Saudi Arabia, Advisor: Peter Richtarik 

• King Abdullah University of Science and Technology (KAUST) August 2020 - December 2021

MS in Applied Mathematics and Computational Sciences Thuwal, Saudi Arabia
Advisor: Peter Richtarik 

• Moscow Institute of Physics and Technology (MIPT) September 2014 - July 2019

BS in Applied Mathematics and Physics Dolgoprudny, Russia, Advisor: Boris Polyak 
Thesis: Averaged Heavy Ball Method

Stochastic Optimization, Distributed Optimization, Federated Learning, Machine Learning

Started his academic path at Specialized Educational Scientific Center of NSU, Russia in 2015, then finished B.S. in Automation of Physical and Technical Research at Novosibirsk State University from 2017–2021, and now doing research in King Abdullah University of Science and Technology, Saudi Arabia while MS and PhD.

Besides his academic work he is an author of "Vectozavr" Youtube channel where he presented his research and some fun projects.

In 2021 he created an online school - vectozavr.ru of physics and math for game developers.

Konstantin Burlachenko obtained an M.S. degree in Computer Science and Control Systems from the Bauman Moscow State University in 2009. 

After his graduation, he worked as a Senior Engineer for Acronis ,Yandex ,NVIDIA, and as a Principal Engineer for HUAWEI. Konstantin attended in Non-Degree Opportunity program at Stanford between 2015 and 2019 and obtained:

• Data, Models and Optimization Graduate Certificate
• Artificial Intelligence Graduate Certificate

One of his sports achievements is the title of candidate Master of Sport in Chess.

Current research interest is mainly focused is on various aspects of Distributed Stochastic Optimization and Federated Learning. The venues that accepted Konstantin’s works include:

• International Conference on Machine Learning (ICML)
• International Conference on Learning Representations (ICLR)
• Transactions on Machine Learning Research (TMLR)
• SIAM Journal on Mathematics of Data Science (SIAM SIMODS)
• ACM International Workshop on Distributed Machine Learning (ACM CoNext)