Ehsan Kazemi
Research Software Engineer
Google Zürich
Experience
Post-Doctoral Fellow (Dec 2016-March 2020), Inference, Information and Decision Systems Group, Yale Institute for Network Science.
I was fortunate to work with a group of prominent researchers (including my adviser Amin Karbasi) on a broad set of machine learning problems such as scalable submodular optimization, applications of deep learning in computational biology and fairness.
Education
Ph.D., Computer, Communication and Information Sciences (2011-2016), Thesis title: “Network Alignment: Theory, Algorithms, and Applications”, Laboratory for Computer Communications and Applications (LCA4), EPFL, Lausanne, Switzerland.
Ph.D. candidate, Computer, Communication and Information Sciences (2010-2011), Unaffiliated Ph.D. student, EPFL, Lausanne, Switzerland, Laboratory for Computer Communications and Applications (LCA1).
MS.c., Electrical Engineering and Communication Systems (2008-2010), Sharif University of Technology, Tehran, Iran.
BS.c., Electrical Engineering and Communication Systems (2004-2008), Sharif University of Technology, Tehran, Iran.
Publications
W. Li, M. Feldman, E. Kazemi, and A. Karbasi. Submodular Maximization in Clean Linear Time. NeurIPS, 2022.
E. Kazemi, S. Minaee, M. Feldman, and A. Karbasi. Regularized Submodular Maximization at Scale. ICML, 2021. [video]
C. Harshaw, E. Kazemi, M. Feldman, and A. Karbasi. The Power of Subsampling in Submodular Maximization. arXiv preprint arXiv:2104.02772, 2021. Mathematics of Operations Research.
P. Khosravi, M. Lysandrou, M. Eljalby, Q. Li, E. Kazemi, P. Zisimopoulos, A. Sigaras, et al. "A Deep Learning Approach to Diagnostic Classification of Prostate Cancer Using Pathology–Radiology Fusion." Journal of Magnetic Resonance Imaging, 2021.
A. Badanidiyuru, A. Karbasi, E. Kazemi, and J. Vondrak. Submodular Maximization Through Barrier Functions. NeurIPS, 2020 (spotlight presentation). [video] [slides] [poster]
R. Haba, E. Kazemi, M. Feldman, and A. Karbasi. Streaming Submodular Maximization under a k-Set System Constraint. ICML, 2020. [video] [slides]
H. Chang, T. D. Nguyen, S. K. Murakonda, E. Kazemi, and R. Shokri. On Adversarial Bias and the Robustness of Fair Machine Learning. arXiv preprint arXiv:2006.08669, 2020.
M. Mitrovic, E. Kazemi, M. Feldman, A. Krause, and A. Karbasi. Adaptive Sequence Submodularity. NeurIPS, 2019. [code] [poster]
E. Kazemi, M. Mitrovic, M. Zadimoghaddam, S. Lattanzi, and A. Karbasi. Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity. ICML, 2019. [code] [poster]
S. Ghili, E. Kazemi, and A. Karbasi. Eliminating Latent Discrimination: Train Then Mask. AAAI, 2019 (oral presentation). [slides] [poster]
E. Kazemi and M. Grossglauser. MPGM: Scalable and Accurate Multiple Network Alignment. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019. [appendix] [publisher link]
P. Khosravi, E. Kazemi, Q. Zhan, J. E. Malmsten, M. Toschi, P. Zisimopoulos, A. Sigaras, S. Lavery, L. A. D. Cooper, C. Hickman, M. Meseguer, Z. Rosenwaks, O. Elemento, N. Zaninovic and I. Hajirasouliha. Deep Learning Enables Robust Assessment and Selection of Human Blastocysts after in Vitro Fertilization. npj Digital Medicine, Nature Publishing Group, 2019. [code]
P. Khosravi, M. Lysandrou, M. Eljalby, M. Brendel, Q. Li, E. Kazemi, J. Barnes, P. Zisimopoulos, A. Sigaras, C. Ricketts, et al. Biopsy-free prediction of prostate cancer aggressiveness using deep learning and radiology imaging. medRxiv, 2019.
M. Feldman, A. Karbasi, and E. Kazemi. Do Less, Get More: Streaming Submodular Maximization with Subsampling. NeurIPS, 2018 (spotlight presentation). [slides] [poster] [video]
P. Khosravi, E. Kazemi, Q. Zhan, M. Toschi, J. E Malmsten, C. Hickman, M. Meseguer, Z. Rosenwaks, O. Elemento, N. Zaninovic, and I. Hajirasouliha. Robust Automated Assessment of Human Blastocyst Quality using Deep Learning. bioRxiv, 2018.
E. Kazemi, M. Zadimoghaddam, and A. Karbasi. Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints. ICML, 2018. [slides] [poster]
M. Mitrovic, E. Kazemi, M. Zadimoghaddam, and A. Karbasi. Data Summarization at Scale: A Two-Stage Submodular Approach. ICML, 2018. [poster]
E. Kazemi, L. Chen, S. Dasgupta, and A. Karbasi. Comparison Based Learning from Weak Oracles. AISTATS, 2018. [slides] [poster]
P. Khosravi, E. Kazemi, M. Imielinski, O. Elemento, and I. Hajirasouliha. Deep Convolutional Neural Networks Enable Discrimination of Heterogeneous Digital Pathology Images. EBioMedicine, 2017. [poster] [code]
E. Kazemi, H. Hassani, M. Grossglauser, and H. Pezeshghi Modarres. PROPER: Global Protein Interaction Network Alignment through Percolation Matching. BMC Bioinformatics, 2016. Website: http://proper.epfl.ch/
E.Kazemi and M. Grossglauser. On the Structure and Efficient Computation of IsoRank Node Similarities. arXiv preprint arXiv:1602.00668, 2016.
E. Kazemi, H. Hassani, and M. Grossglauser. Growing a Graph Matching from a Handful of Seeds. VLDB, 2015. [slides] [poster]
E. Kazemi, L. Yartseva, and M. Grossglauser. When Can Two Unlabeled Networks Be Aligned under Partial Overlap? Annual Allerton Conference on Communication, Control, and Computing, 2015. [slides]
R. Shokri, G. Theodorakopoulos, P. Papadimitratos, E. Kazemi, and J. P. Hubaux. Hiding in the mobile crowd: Location privacy through collaboration. IEEE Transactions on Dependable and Secure Computing, 2014.
M. Kafsi, E. Kazemi, L. Maystre, L. Yartseva, M. Grossglauser, and P. Thiran. Mitigating Epidemics through Mobile Micro-Measures. Third International Conference on the Analysis of Mobile Phone Datasets, 2013. [poster]
V. Etter, M. Kafsi, E. Kazemi, M. Grossglauser, and P. Thiran. Where to Go from Here? Mobility Prediction from Instantaneous Information. Pervasive and Mobile Computing, 2013.
V. Etter, M. Kafsi, and E. Kazemi. Been There, Done That: What Your Mobility Traces Reveal about Your Behavior. Mobile Data Challenge by Nokia Workshop, in conjunction with Int. Conf. on Pervasive Computing, 2012. [poster]