Scholar
Eitan Levin
Google Scholar ID: UraAgrEAAAAJ
California Institute of Technology
Citations & Impact
Citations
280
H-index
9
i10-index
9
Publications
16
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Any-dimensional polynomial optimization via de Finetti theorems (Submitted, 2025)
- Poset-Markov channels: capacity via group symmetry (Submitted, 2025)
- On transferring transferability: towards a theory for size generalization (NeurIPS, 2025, Spotlight)
- Dimension-free descriptions of convex sets (Submitted, 2024)
- Any-dimensional equivariant neural networks (AISTATS, 2024)
- The effect of smooth parametrizations on nonconvex optimization landscapes (Mathematical Programming, 2024, INFORMS Optimization Society Student Paper Prize)
- Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy (Mathematical Programming, 2023)
- Towards optimization on varieties (Undergraduate senior thesis, Princeton University, 2020)
- A note on Douglas-Rachford, gradients, and phase retrieval (arXiv:1911.13179, 2019)
- Multi-target detection with application to cryo-electron microscopy (Inverse Problems, 2019)
- Toward single particle reconstruction without particle picking: breaking the detection limit (SIAM Journal on Imaging Sciences, 2023)
- 3D ab initio modeling in cryo-EM by autocorrelation analysis (2018 IEEE 15th International Symposium on Biomedical Imaging, 2018, Best Student Paper)
- Direct reconstruction of two-dimensional currents in thin films from magnetic-field measurements (Physical Review Applied, 2017)
- Stopping criterion for iterative regularization of large-scale ill-posed problems using the Picard parameter (arXiv:1707.04200, 2017)
- Estimation of the regularization parameter in linear discrete ill-posed problems using the Picard parameter (SIAM Journal on Scientific Computing, 2017)
Research Experience
- Involved in various research projects including but not limited to: any-dimensional polynomial optimization, poset-Markov channels, nonconvex optimization landscapes, and more.
Education
- Graduate student in Applied and Computational Math at Caltech, advised by Venkat Chandrasekaran; Undergraduate senior thesis at Princeton University titled 'Towards optimization on varieties'.
Background
- Graduate student in Applied and Computational Math at Caltech, focusing on the mathematics of data science and machine learning, drawing on ideas from optimization, geometry, algebra, and probability.
Miscellany
- Personal interests and other information not provided.
