Manolis Tsakiris 助理教授、研究员




  • Theoretical foundations of data science

  • Machine learning and signal processing

  • Commutative algebra and algebraic geometry


Manolis Tsakiris毕业于希腊国立雅典理工大学电气工程和计算机科学专业。他在英国帝国理工大学获得信号处理领域的硕士学位,在美国约翰霍普金斯大学获得理论机器学习领域的博士学位,师从Rene Vidal教授。20178月,他加入了上海科技大学信息科学与技术学院担任助理教授。他的研究兴趣包括子空间学习的基本理论,以及其在机器学习和数据科学的应用。重要的例子包括鲁棒主成分分析、子空间聚类、乱序线性回归(Shuffled Linear Regression)和矩阵补全。受到子空间布局模型在机器学习领域成功的启发,他也在研究纯粹数学中关于相关簇的代数几何不变量的问题,例如这些相关簇的Castelnuovo-Mumford正则性。  

Manolis Tsakiris is an electrical engineering and computer science graduate of the National Technical University of Athens, Greece. He holds an MS degree in signal processing from Imperial College London, UK, and a PhD degree in theoretical machine learning from Johns Hopkins University, USA, under the supervision of Prof. Rene Vidal. Since August 2017 he is an assistant professor at the School of Information Science and Technology (SIST) at ShanghaiTech University. His research focuses on fundamental theoretical aspects of subspace learning methods, with applications in machine learning and data science. Prominent examples include Robust Principal Component Analysis, Subspace Clustering, Shuffled Linear Regression and Matrix Completion. Inspired by the success of the union of subspaces model in machine learning, he is also working on purely mathematical problems concerning algebraic-geometric invariants of related algebraic varieties, such as their Castelnuovo-Mumford regularity.


  1. T. Ding, Y. Yang, Z. Zhu, D. Robinson, R. Vidal, L. Kneip, M. C. Tsakiris, Robust homography estimation via dual principal component pursuit, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.

  2. M. C. Tsakiris, L. Peng, A. Conca, L. Kneip, Y. Shi, H. Choi, “An algebraic-geometric approach to linear regression without correspondences”, IEEE Transactions on Information Theory (TIT), 2020.

  3. M. C. Tsakiris, “Linearization of resolutions via products”, Journal of Pure and Applied Algebra, 2020.

  4. M. C. Tsakiris and L. Peng, “Homomorphic sensing”, International Conference on Machine Learning (ICML), 2019.

  5. Z. Zhu, Y. Wang, D. P. Robinson, D. Naiman, R. Vidal, M. C. Tsakiris, “Dual principal component pursuit: Improved analysis and efficient algorithms”, Neural Information Processing Systems (NeurIPS), 2018.

  6. M. C. Tsakiris and R. Vidal, “Dual principal component pursuit”, Journal of Machine Learning Research (JMLR), 2018.

  7. M. C. Tsakiris and R. Vidal, “Theoretical analysis of sparse subspace clustering with missing entries”, International Conference on Machine Leanring (ICML), 2018.

  8. M. C. Tsakiris and R. Vidal. “Hyperplane clustering via dual principal component pursuit”, International Conference on Machine Learning (ICML), 2017.

  9. M. C. Tsakiris and R. Vidal, “Algebraic clustering of affine subspaces”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017.

  10. M. C. Tsakiris and R. Vidal, “Filtrated algebraic subspace clustering”, SIAM Journal of Imaging Sciences, 2017.