Research Publications

Submitted

1. D. Davis, D. Drusvyatskiy and V. Charisopoulos. “Stochastic algorithms with geometric step decay converge linearly on sharp functions.” (2019), arXiv: 1907.09547. [Code].

2. V. Charisopoulos, A. R. Benson and A. Damle. “Incrementally Updated Spectral Embeddings.” (2019), arXiv: 1909.01188. [Code].

3. V. Charisopoulos and P. Maragos. “A Tropical Approach to Neural Networks with Piecewise Linear Activations.” (2018), arXiv: 1805.08749

Journals

1. V. Charisopoulos and D. Davis. “A superlinearly convergent subgradient method for sharp semismooth problems,” Mathematics of Operations Research (to appear), 2022, arXiv: 2201.04611. [Code].

2. P. Maragos, V. Charisopoulos and E. Theodosis, “Tropical Geometry and Machine Learning,” Proceedings of the IEEE, pp. 728-755, vol. 109, no. 5, 2021, doi: 10.1109/JPROC.2021.3065238.

3. V. Charisopoulos, Y. Chen, D. Davis, M. Díaz, L. Ding and D. Drusvyatskiy, “Low-Rank Matrix Recovery with Composite Optimization: Good Conditioning and Rapid Convergence,” Foundations of Computational Mathematics, Jan. 2021, doi: 10.1007/s10208-020-09490-9. [Code].

4. V. Charisopoulos, Austin R. Benson and A. Damle, “Communication-efficient distributed eigenspace estimation,” SIAM Journal on Mathematics of Data Science, pp. 1067-1092, vol. 3, no.4, 2021, doi: 10.1137/20M1364862. [Code].

5. V. Charisopoulos, D. Davis, M. Díaz and D. Drusvyatskiy, “Composite optimization for robust rank one bilinear sensing,” Information and Inference: A Journal of the IMA, pp. 333-396, vol. 10, no. 2, 10. 2020, doi: 10.1093imaiaiiaaa027. [Code].

6. A. Nikas, H. Doukas, J. Lieu, R. Alvarez Tinoco, V. Charisopoulos and W. van der Gaast, “Managing stakeholder knowledge for the evaluation of innovation systems in the face of climate change,” Journal of Knowledge Management, pp. 1013–1034, vol. 21, no. 5, 2017, doi: 10.1108/JKM-01-2017-0006.

Conferences

1. V. Charisopoulos and A. Damle. “Communication-efficient distributed eigenspace estimation with arbitrary node failures,” in Advances in Neural Information Processing Systems (to appear, 2022), arXiv: 2206.00127.

2. V. Charisopoulos, A. R. Benson and A. Damle, “Entrywise convergence of iterative methods for eigenproblems,” in Advances in Neural Information Processing Systems, , pp. 5644–5655, vol. 33, 2020. [Code].

3. V. Charisopoulos and P. Maragos, “Morphological perceptrons: geometry and training algorithms”, in Proceedings of International Symposium on Mathematical Morphology and its applications to signal and image processing, pp. 3–15, 2017, doi: 10.1007978-3-319-57240-6_1