Peter Richtarik
| Peter Richtarik | |
|---|---|
| Born | Nitra, Slovakia |
| Nationality | Slovak |
| Fields | Mathematician, Computer Scientist |
| Alma mater | Comenius University Cornell University |
| Academic advisors | Yurii Nesterov |
Peter Richtarik is a Slovak mathematician working in the area of big data optimization and machine learning, known for his work on randomized coordinate descent algorithms. He is currently a reader in the School of Mathematics at the University of Edinburgh.[1]
Education
Richtarik earned a master's degree in mathematics from Comenius University, Slovakia, in 2001, graduating summa cum laude.[2] In 2007, he obtained a PhD in operations research from Cornell University, advised by Michael Jeremy Todd.[3][4] Between 2007 and 2009, he was a postdoctoral scholar in the Center for Operations Research and Econometrics and Department of Mathematical Engineering at Universite catholique de Louvain, Belgium, working with Yurii Nesterov.[5][6]
Career
Since 2009, Richtarik has been working at the University of Edinburgh. He is a Faculty Fellow of the Alan Turing Institute and the Head of a big data optimization group at the University.[7] Richtarik founded and organizes a conference series entitled "Optimization and Big Data".[8][9]
Academic work
Richtarik's early research concerned gradient-type methods, optimization in relative scale, sparse principal component analysis and algorithms for optimal design. Since his appointment at Edinburgh, he has been working extensively on building algorithmic foundations of randomized methods in convex optimization, especially randomized coordinate descent algorithms. These methods are well suited for optimization problems described by big data, and have applications in fields such as machine learning, signal processing and data science.[10][11] Richtarik is the co-inventor of an algorithm generalizing the randomized Kaczmarz method for solving a system of linear equations.
Awards and distinctions
- 2016, SIGEST Award (jointly with Olivier Fercoq)[12] of the Society for Industrial and Applied Mathematics
- 2016, EPSRC Early Career Fellowship in Mathematical Sciences[13]
- 2015, EUSA Best Research or Dissertation Supervisor Award (2nd place)[14]
- 2014, Plenary Talk at 46th Conference of Slovak Mathematicians[15]
Bibliography
- Peter Richtarik & Martin Takac (2012). "Efficient serial and parallel coordinate descent methods for huge-scale truss topology design" (pdf). Operations Research Proceedings 2011. Springer-Verlag. pp. 27–32.
- Peter Richtarik & Martin Takac (2014). "Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function" (pdf). Mathematical Programming. 144 (1). Springer. pp. 1–38.
- Olivier Fercoq & Peter Richtarik (2015). "Accelerated, parallel and proximal coordinate descent" (pdf). SIAM Journal on Optimization. 25 (4). pp. 1997–2023.
- Dominik Csiba; Zheng Qu; Peter Richtarik (2015). "Stochastic Dual Coordinate Ascent with Adaptive Probabilities" (pdf). Proceedings of The 32nd International Conference on Machine Learning. pp. 674–683.
- Robert M Gower & Peter Richtarik (2015). "Randomized Iterative Methods for Linear Systems" (pdf). SIAM Journal on Matrix Analysis and Applications. 36 (4). pp. 1660–1690.
- Peter Richtarik & Martin Takac (2016). "Parallel coordinate descent methods for big data optimization" (pdf). Mathematical Programming. 156 (1). pp. 433–484.
- Zheng Qu & Peter Richtarik (2016). "Coordinate descent with arbitrary sampling I: algorithms and complexity" (pdf). Optimization Methods and Software. 31 (5). pp. 829–857.
- Zheng Qu & Peter Richtarik (2016). "Coordinate descent with arbitrary sampling II: expected separable overapproximation" (pdf). Optimization Methods and Software. 31 (5). pp. 858–884.
- Zheng Qu; Peter Richtarik; Martin Takac; Olivier Fercoq (2016). "SDNA: Stochastic Dual Newton Ascent for Empirical Risk Minimization" (pdf). Proceedings of The 33rd International Conference on Machine Learning. pp. 1823–1832.
- Zeyuan Allen-Zhu; Zheng Qu; Peter Richtarik; Yang Yuan (2016). "Even faster accelerated coordinate descent using non-uniform sampling" (pdf). Proceedings of The 33rd International Conference on Machine Learning. pp. 1110–1119.
- Dominik Csiba & Peter Richtarik (2016). "Importance sampling for minibatches". arXiv:1602.02283
[cs.LG]. - Dominik Csiba & Peter Richtarik (2016). "Coordinate descent face-off: primal or dual?". arXiv:1605.08982 [math.OC].
References
- ↑ "Website of the School of Mathematics, The University of Edinburgh". Retrieved August 22, 2016.
- ↑ "Richtarik's CV" (PDF). Retrieved August 21, 2016.
- ↑ "Mathematics Genealogy Project". Retrieved August 20, 2016.
- ↑ "Cornell PhD Thesis". Retrieved August 22, 2016.
- ↑ "Postdoctoral Fellows at CORE". Retrieved August 22, 2016.
- ↑ "Simons Institute for the Theory of Computing, UC Berkeley". Retrieved August 22, 2016.
- ↑ "Alan Turing Institute Faculty Fellows". Retrieved August 22, 2016.
- ↑ "Optimization and Big Data 2012". Retrieved August 20, 2016.
- ↑ "Optimization and Big Data 2015". Retrieved August 20, 2016.
- ↑ Cathy O'Neil & Rachel Schutt (2013). "Modeling and Algorithms at Scale". Doing Data Science: Straight Talk from the Frontline. O'Reilly. Retrieved August 21, 2016.
- ↑ Sebastien Bubeck (2015). Convex Optimization: Algorithms and Complexity. Foundations and Trends in Machine Learning. Now Publishers. ISBN 1601988605.
- ↑ "SIGEST Award". Retrieved August 20, 2016.
- ↑ "EPSRC Fellowship". Retrieved August 21, 2016.
- ↑ "EUSA Awards 2015". Retrieved August 20, 2016.
- ↑ "46th Conference of Slovak Mathematicians". Retrieved August 22, 2016.
External links
- Richtarik's web page at University of Edinburgh.
- Richtarik's Google Scholar profile