Research Interests

I am interested in developing and applying mathematical tools and machine learning algorithms to challenging problems.

Research Papers

  • TopTemp: Parsing Precipitate Structure from Temper Topology by L. Kassab, S. Howland, H. Kvinge, K. Sahithi Kappagantula, T. Emerson. To appear in the 2022 ICLR Workshop on Geometric and Topological Representation Learning. [arXiv:2204.00629]
  • Weakly-Supervised Object Localization using Semi-Supervised Non-Negative Matrix Factorization by E. Sizikova, J. Vendrow, R. Grotheer, J. Haddock, L. Kassab, A. Kryshchenko, T. Merkh, M. Rajapaksha, H. V. Vo, C. Wang , K. Leonard, D. Needell. Submitted, 2021.
  • Detecting Short-Lasting Topics using Nonnegative Tensor Decomposition by L. Kassab, A. Kryshchenko, H. Lyu, D. Molitor, D. Needell, E. Rebrova. Submitted, 2021. [arXiv: 2010.01600]
  • Semi-supervised NMF Models for Topic Modeling in Learning Tasks ​by J. Haddock, L. Kassab, S. Li, A. Kryshchenko, R. Grotheer, E. Sizikova, C. Wang, T. Merkh, R. W. M. A. Madushani, M. Ahn, D. Needell, K. Leonard. Proc. 55th Asilomar Conf. on Signals, Systems, and Computers, Pacific Grove, CA, Nov. 2021.  [arXiv: 2010.07956, PyPI package].
  • On Large-Scale Dynamic Topic Modeling with Nonnegative CP Tensor Decomposition by M. Ahn, N. Eikmeier, J. Haddock, L. Kassab, A. Kryshchenko, K. Leonard, D. Needell, R. W. M. A. Madushani, E. Sizikova, C. Wang. Proc. Women in Data Science and Mathematics, Advances in Data Science, AWM-Springer series, 2020. [arXiv: 2001.00631]
  • An Adaptation for Iterative Structured Matrix Completion by H. Adams,  L. Kassab, D. Needell. Journal version published in Foundations of Data Science 3:769–791, 2021. Conference version published in Proc. 54th Asilomar Conf. on Signals, Systems and Computers, Pacific Grove, CA, Nov. 2020. [arXiv:2002.02041, MATLAB code]
  • On Nonnegative CP Tensor Decomposition Robustness to Noise by J. Haddock,  L. Kassab, A. Kryshchenko, D. Needell. Proc. Information Theory and Applications (ITA), San Diego, CA, February 2020.
  • A torus model for optical flow by H. Adams, J. Bush, B. Carr,  L. Kassab, J. Mirth. Journal version published in Pattern Recognition Letters 129:304-310, 2020. Conference version On the nonlinear statistics of optical flow published in Proceedings of Computational Topology in Image Context, LNCS volume 11382:151-165, 2019.​ ​[Journal Version Link, Conference Version Link, arXiv:1812.00875, Software]