Anastasios Kyrillidis


Research interests:


  • machine learning
  • convex and non-convex analysis and optimization
  • data analytics and mining
  • structured low dimensional models
  • compressed sensing


Anastasios Kyrillidis received his 5-year diploma and M.Sc. in Electronic and Computer Engineering from Technical University of Crete in 2008 and 2010, respectively. He was the first PhD student to graduate from the LIONS. Currently, he is Simons Foundation PostDoc Fellow at The University of Texas at Austin. His research interests includes convex and non-convex optimization, low-dimensional modeling in machine learning, and large-scale data analysis and processing. 



Quoc Tran-Dinh; A. Kyrillidis; V. Cevher : A Single-Phase, Proximal Path-Following Framework; Mathematics Of Operations Research. 2018-11-01. DOI : 10.1287/moor.2017.0907.
Y.-P. Hsieh; Y.-C. Kao; R. Karimi Mahabadi; Y. Alp; A. Kyrillidis et al. : A Non-Euclidean Gradient Descent Framework for Non-Convex Matrix Factorization; IEEE Transactions on Signal Processing. 2018. DOI : 10.1109/TSP.2018.2870353.
Q. Tran Dinh; A. Kyrillidis; V. Cevher : A single-phase, proximal path-following framework; Mathematics of Operations Research. 2017.
A. Kyrillidis; B. Bah; R. Hasheminezhad; Q. Tran Dinh; L. Baldassarre et al. : Convex block-sparse linear regression with expanders - provably. 2016. The 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016), Cadiz, Spain, May 7-11, 2016.
L. Baldassarre; N. Bhan; V. Cevher; A. Kyrillidis : Group-Sparse Model Selection: Hardness and Relaxations; IEEE Transactions on Information Theory. 2016. DOI : 10.1109/TIT.2016.2602222.
Q. Tran Dinh; A. Kyrillidis; V. Cevher : Composite Self-Concordant Minimization; Journal of Machine Learning Research. 2015.
A. Kyrillidis; M. Vlachos; A. Zouzias : Approximate Matrix Multiplication with Application to Linear Embeddings. 2014. IEEE International Symposium on Information Theory (ISIT), Honolulu, HI, JUN 29-JUL 04, 2014. p. 2182-2186.
A. Kyrillidis / V. Cevher (Dir.) : Rigorous optimization recipes for sparse and low rank inverse problems with applications in data sciences. Lausanne, EPFL, 2014. DOI : 10.5075/epfl-thesis-6350.
A. Kyrillidis; G. N. Karystinos : Fixed-Rank Rayleigh Quotient Maximization by an MPSK Sequence; IEEE Transactions on Communications. 2014. DOI : 10.1109/Tcomm.2014.012414.130439.
A. Kyrillidis; R. Karimi Mahabadi; Q. Tran Dinh; V. Cevher : Scalable sparse covariance estimation via self-concordance. 2014. Twenty-Eighth AAAI Conference on Artificial Intelligence, Quebec, Canada, July 27-31, 2014.
A. Kyrillidis; V. Cevher : Matrix Recipes for Hard Thresholding Methods; Journal Of Mathematical Imaging And Vision. 2014. DOI : 10.1007/s10851-013-0434-7.
Q. Tran Dinh; A. Kyrillidis; V. Cevher : An inexact proximal path-following algorithm for constrained convex minimization; Siam Journal On Optimization. 2014. DOI : 10.1137/130944539.
A. Kyrillidis; S. Becker; V. Cevher; C. Koch : Sparse projections onto the simplex. 2013. The 30th International Conference on Machine Learning (ICML) 2013, Atlanta, USA, June 16-21, 2013. p. 280-288.
A. Kyrillidis; V. Cevher : Fast Proximal Algorithms For Self-Concordant Function Minimization With Application To Sparse Graph Selection. 2013. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada, May 26-31, 2013. p. 6585-6589. DOI : 10.1109/ICASSP.2013.6638935.
A. Kyrillidis; V. Cevher : Fast Proximal algorithms for Self-concordant function minimization with application to sparse graph selection. 2013. 38th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, Canada, May 26-31, 2013.
S. Becker; V. Cevher; A. Kyrillidis : Randomized Low-Memory Singular Value Projection. 2013. 10th International Conference on Sampling Theory and Applications (Sampta), Bremen, Germany, July 1st - July 5th, 2013.
Q. Tran Dinh; A. Kyrillidis; V. Cevher : A proximal Newton framework for composite minimization: Graph learning without Cholesky decompositions and matrix inversions. 2013. 30th International Conference on Machine Learning, Atlanta, GA, USA, June 16-19, 2013.
N. D. Sidiropoulos; A. Kyrillidis : Multi-Way Compressed Sensing for Sparse Low-Rank Tensors; IEEE Signal Processing Letters. 2012. DOI : 10.1109/Lsp.2012.2210872.
A. Kyrillidis; G. Puy; V. Cevher : Hard Thresholding with Norm Constraints. 2012. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, March, 2012. p. 3645-3648. DOI : 10.1109/ICASSP.2012.6288706.
A. Kyrillidis; V. Cevher : Matrix ALPS: Accelerated Low Rank and Sparse Matrix Reconstruction. 2012. IEEE Statistical Signal Processing Workshop (SSP), Ann Arbor, Michigan, USA, August, 2012. p. 185-188. DOI : 10.1109/SSP.2012.6319655.
A. Kyrillidis; V. Cevher : Combinatorial Selection and Least Absolute Shrinkage via the CLASH Algorithm. 2012. 2012 IEEE International Symposium on Information Theory Proceedings (ISIT), Cambridge, Massachusetts, USA, July 1-6, 2012. p. 2216-2220. DOI : 10.1109/ISIT.2012.6283847.
A. Kyrillidis; V. Cevher : Recipes on Hard Thresholding Methods. 2011. 4th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), Puerto Rico, December, 2011. DOI : 10.1109/CAMSAP.2011.6136024.
A. T. Kyrillidis; G. N. Karystinos : Rank-Deficient Quadratic-Form Maximization Over M-Phase Alphabet: Polynomial-Complexity Solvability And Algorithmic Developments. 2011. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Prague, Czech Republic, May 22-27, 2011. p. 3856-3859. DOI : 10.1109/ICASSP.2011.5947193.