Evgenii Tsymbalov

PhD graduate 2020

Graduated from: Higher School of Economics

Research interests: machine learning, elastic strain engineering, active learning, industrial data analysis

Thesis title: Machine learning for elastic strain engineering

Academic mobility:

MIT, Ju Li research group (http://li.mit.edu/) 11.2017 – 12.2017; 08.2018 – 09.2018

Publications

Tsymbalov E., Makarychev S., Shapeev A., Panov M. Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Main track. Pages 3599-3605, 2019.

Shi, Z., Tsymbalov, E., Dao, M., Suresh, S., Shapeev, A., & Li, J. (2019). Deep elastic strain engineering of bandgap through machine learning. Proceedings of the National Academy of Sciences, 116(10), 4117-4122.

Tsymbalov, E., Panov, M., & Shapeev, A. (2018, July). Dropout-Based Active Learning for Regression. In International Conference on Analysis of Images, Social Networks and Texts (pp. 247-258). Springer, Cham.

Gordin, V. A., & Tsymbalov, E. A. (2018). Compact difference scheme for parabolic and Schrödinger-type equations with variable coefficients. Journal of Computational Physics, 375, 1451-1468.

Conferences:

Tsymbalov E., Shapeev A., Panov M. Gaussian Processes and Decorrelation Masks: a Way to Enhance Dropout Uncertainty Estimate // Machine Learning Summer School, Skoltech, Moscow, Russia, August 26 – September 9, 2019

Tsymbalov E., Shi Z., Dao M., Suresh S., Li J., Shapeev A. Elastic Strain Engineering of Diamond: Tracking Treasure Down // Inaugural Symposium for Computational Materials Program of Excellence, Skoltech, Moscow, Russia, September 4 – 6, 2019

Tsymbalov E., Makarychev S., Panov M., Shapeev A. Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning Learning // 28th International Joint Conference on Artificial Intelligence. Main track. Macao, China, 2019

Tsymbalov E., Makarychev S., Panov M., Shapeev A. Deeper Connections between Neural Networks and Gaussian Processes Speed-up Active Learning // 36th International Conference on Machine Learning Workshop on Uncertainty & Robustness in Deep Learning, Long Beach, California, USA, June 14, 2019 (remote)

Tsymbalov E., Shi Z., Dao M., Suresh S., Shapeev A., & Li J. Neural networks for elastic strain engineering // “Application of Machine-Learning Interatomic Potentials in Materials Design” International Workshop, Skoltech, Moscow, Russia, June 6, 2019.

Tsymbalov E., Shi Z., Shapeev A., Li J. Deep Elastic Strain Engineering for Optimization and Exploration of Semiconductors Electronic Properties // III International Workshop on Electromagnetic Properties of Novel Materials, Skoltech, Moscow, Russia, December 18-20, 2018.

Shi Z., Tsymbalov E., Shapeev A., Li J. Elastic Strain Engineering Reaches Six Dimensions via Machine Learning // 2018 Materials Research Society Fall Meeting, MIT, Boston, US, November 27, 2018.

Tsymbalov E., Ushakov R., Shapeev A., Panov M. Deep Active Learning: Gaussian Processes to the Rescue! // 3rd Annual MIT-Skoltech Conference: “Collaborative Solutions for Next Generation Education, Science and Technology”, Moscow, Russia, October 15-16, 2018.

Tsymbalov E., Shi Z., Shapeev A., Li J. Machine Learning Elastic Strain Engineering (E. Tsymbalov, A. Shapeev, J. Li, Z. Shi) in 3rd Annual MIT-Skoltech Conference: “Collaborative Solutions for Next Generation Education, Science and Technology”, Moscow, Russia, October 15-16, 2018.

Tsymbalov E., Panov M., Shapeev A. Dropout-based Active Learning for Regression // 7th International Conference – Analysis of Images, Social networks and Texts, July 5-7, Moscow, Russia

Tsymbalov E., Panov M., Shapeev A. Dropout-based Active Learning for Regression // 7th Symposium On Conformal & Probabilistic Prediction With Applications (COPA 2018), June 11-13, 2018, Maastricht, Netherlands

Tsymbalov E. Compact high-order difference approximations for rod lateral vibrations equation // International Conference on Computer Simulation in Physics and beyond, October 9-12, 2017, Moscow, Russia

Tsymbalov E., Shapeev A. Surrogate modelling of Si and Ge electronic properties under elastic strain // International Conference on Computer Simulation in Physics and beyond, October 9-12, 2017, Moscow, Russia

Tsymbalov E., Shi Z., Shapeev A., Li J. Material strain optimization meets machine learning // Gen-Y: Skoltech Young Scientist Cross-Disciplinary Conference, September 27 – October 1, 2017, Sochi, Russia

Tsymbalov E., Shapeev A. Machine learning for approximation of Si energy bands // 14th Russian Symposium FAMMS-2017: Foundations of Atomistic Multiscale Modeling and Simulation, August 16-27, 2017, New Athos, Abkhazia

Tsymbalov E., Baymurzina D., Shapeev A. Machine learning strain engineering // Shaping the Future: Big Data, Biomedicine and Frontier Technologies, April 25-26, Skolkovo Innovation Center, Moscow