Professor Mihai Cucuringu

Associate Professor of Statistics

Biographical Sketch

I finished my Ph.D. in Applied and Computational Mathematics (PACM) at Princeton University in 2012. I joined the Department of Statistics in 2018, and have also been an affiliated faculty at the Mathematical Institute and the Institute for New Economic Thinking. Prior to this

2017-2018 Turing Research Fellow, The Alan Turing Institute in London, and Department of Statistics and Mathematical Institute, University of Oxford
2013-2016 CAM Assistant Adjunct Professor, Department of Mathematics, UCLA
Fall 2014 Research Fellow, Simons Institute for Theory of Computing, UC Berkeley, in the program Algorithmic Spectral Graph Theory
Spring 2014 Research Fellow, ICERM, Brown University, in the program Network Science and Graph Algorithms
2012-2013 Associate Quantitative Researcher, Statistical Arbitrage, Quantitative Trading Group, Bank of America Merrill Lynch, New York

Research Interests

I am interested in the development and mathematical & statistical analysis of algorithms that extract information from massive noisy data sets, network analysis, and certain computationally-hard inverse problems on large graphs. Applications include various problems in machine learning, statistics, finance, and engineering, often with an eye towards extracting structure from time-dependent data which can be subsequently leveraged for prediction purposes. More specifically, I have considered problems that span

spectral and semidefinite programming relaxation algorithms and applications to ranking, clustering, group synchronization, phase unwrapping
networks, community and core-periphery structure, network time series
nonlinear dimensionality reduction and diffusion maps, intrinsic slow variables in dynamic data
statistical analysis of big financial data, statistical arbitrage, market microstructure, limit order books, risk models
low-rank matrix completion, distance geometry problems, rigidity theory, sensor network localization and 3D structuring of molecules

Publications

Oliveira, D., Lu, Y., Lin, X., Cucuringu, M. and Fujita, A. (2024) “Causality-Inspired Models for Financial Time Series Forecasting”, arXiv.

Clarkson, J., Xu, W., Cucuringu, M. and Reinert, G. (2024) “Split Conformal Prediction under Data Contamination”, arXiv.

Lu, Y., Reinert, G. and Cucuringu, M. (2024) “Trade co-occurrence, trade flow decomposition, and conditional order imbalance in equity markets”, Quantitative Finance, 24(6), pp. 779–809.

Araya, E., Cucuringu, M. and Tyagi, H. (2024) “Dynamic angular synchronization under smoothness constraints”, arXiv.

Cucuringu, M., Dong, X. and Zhang, N. (2024) “Maximum Likelihood Estimation on Stochastic Blockmodels for Directed Graph Clustering”, arXiv.

Crook, O., Cucuringu, M., Hurst, T., Schönlieb, C.-B., Thorpe, M. and Zygalakis, K. (2024) “A linear transportation L p distance for pattern recognition”, Pattern Recognition, 147(SIAM J. Math. Anal. 49 2 2017), p. 110080.

Ouyang, R., Elliott, A., Limnios, S., Cucuringu, M. and Reinert, G. (2024) “L2G2G: a Scalable Local-to-Global Network Embedding with Graph Autoencoders”, arXiv.

Vuletić, M., Prenzel, F. and Cucuringu, M. (2024) “Fin-GAN: forecasting and classifying financial time series via generative adversarial networks”, Quantitative Finance, 24(2), pp. 175–199.

Ouyang, R., Elliott, A., Limnios, S., Cucuringu, M. and Reinert, G. (2024) “L2G2G: A Scalable Local-to-Global Network Embedding with Graph Autoencoders”, in Complex Networks & Their Applications XII. Springer Nature, pp. 400–412.

He, Y., Reinert, G., Wipf, D. and Cucuringu, M. (2024) “ROBUST ANGULAR SYNCHRONIZATION VIA DIRECTED GRAPH NEURAL NETWORKS”, in 12th International Conference on Learning Representations, ICLR 2024.