- arXivLottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable NetworksarXiv preprint arXiv:2206.01278 2022Spotlight presentation at the Sparsity in Neural Networks (SNN) Workshop 2022.
- PLOS Comp BioTowards a more general understanding of the algorithmic utility of recurrent connectionsPLOS Computational Biology 2022Poster presentation at COSYNE 2019.
- ICLRHow many degrees of freedom do we need to train deep networks: a loss landscape perspectiveInternational Conference on Learning Representations (ICLR) 2022
- SIMAXPractical leverage-based sampling for low-rank tensor decompositionarXiv preprint arXiv:2006.16438 2020To appear in SIAM Journal on Matrix Analysis and Applications
- arXivAvoiding Spurious Local Minima in Deep Quadratic NetworksarXiv preprint arXiv:2001.00098 2019Oral presentation at Deep Math 2020.
- ThesisGraph-Based Clustering: Distributed Algorithms for Balanced Graph Cuts2016
- SPIEApplying matching pursuit decomposition time-frequency processing to UGS footstep classificationIn Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense XII 2013