I am an Assistant Adjunct Professor in the UCLA Department of Mathematics. I am also a member of the UCLA Computer Vision Lab, working with Professor. Stefano Soatto.
Contact Info:
University of California, Los Angeles (UCLA), Department of Mathematics
Mathematical Sciences Building, room 5338
520 Portola Plaza, Los Angeles, CA 90095.
Email: shaydeu@math.ucla.edu
Research Interests
My research is primarily related to multi-scale representation and robust statistical estimation applied to developing graph based methods for unsupervised learning. I currently focus on problems that are in the union of network analysis and graph signal processing, and their application to zero shot learning and computational biology.
Education
I completed my PhD in the Computer Science Department at the University of Southern California. My thesis advisor was Professor Gerard Medioni with whom I was working on developing a global framework for Tensor Voting, and on Manifold Learning. I also collaborated with Professor Antonio Ortega on developing a new framework for Manifold Denoising using tools from Graph Signal Processing.
Publications
S. Deutsch, S. Soatto, "Graph Spectral Embedding using the Geodesic Betweenness Centrality", Accepted to AISTATS 2023 [pdf].
Jeffrey N. Law, Kyle Akers, Nure Tasnina, Catherine M. Della-Santina, Shay Deutsch, Meghana Kshirsagar, Judith Klein-Seetharaman, Mark Crovella, Padmavathy Rajagopalan, Simon Kasif, T. M. Murali, "Interpretable Network Propagation with Application to Expanding the Repertoire of Human Proteins that Interact with SARS-CoV-2". In GigaScience 2021.
S. Deutsch, S. Soatto. "Spectral Embedding of Graph Networks", preprint, [pdf].
S. Deutsch, A. Bertozzi and S. Soatto,"Zero Shot Learning Using the Isoperimetric Loss", AAAI-20, [pdf].
S. Deutsch, I. Masi and S. Soatto, "Finding Structure in Point Cloud Data with the Robust Isoperimetric Loss", Scale Space and Variational Methods in Computer Vision (SSVM19) [pdf].
S. Deutsch, A.Ortega and G.Medioni, "Robust Denoising of Piece-Wise Smooth Manifolds", ICASSP 2018, [pdf].
S. Deutsch, S. Kolouro, K. Kynugnam, Y. Owechko, and S. Soatto, “Zero-Shot Learning Via Multi-Scale Manifold Regularization”, CVPR 2017, pp. 7112-7119, [pdf].
S. Deutsch, A. Ortega, and G. Medioni. “Graph Manifold Based Frequency Analysis For Denoising", Submitted.
S. Deutsch and G. Medioni. "Learning the Geometric Structure of Manifolds with Singularities Using the Tensor Voting Graph", Journal of Mathematical Imaging and Vision 2017, 402-422.
S. Deutsch, A. Ortega, and G. Medioni. “Manifold Denoising Based on Spectral Graph Wavelets", ICASSP 2016.
S. Deutsch and G. Medioni. “Intersecting Manifolds: Detection, Segmentation, and Labeling”, International Joint Conference on Artificial Intelligence, (IJCAI), 2015. [pdf].
S. Deutsch and G. Medioni. “Unsupervised Learning Using the Tensor Voting Graph”, Scale Space and Variational Methods in Computer Vision (SSVM), 2015 [pdf].
A. Averbuch, S. Dekel and S.Deutsch. “Adaptive Compressed Image Sensing Using Dictionaries”. Siam Journal Of Imaging Sciences, 5(1), (2012), 57-89 [pdf].
S. Deutsch, A. Averbuch and S. Dekel. “Adaptive compressed image sensing based on wavelet modeling and direct sampling.”, Sampling Theory and Applications (SAMPTA) Conference, 2009 [pdf].
Teaching
Fall 2021: MATH 151A - Applied Numerical Methods (I)
Spring 2021: MATH 151B - Applied Numerical Methods (II)
Spring 2021: MATH 115A - Linear Algebra
Winter 2021: MATH 151A - Applied Numerical Methods (I)
Fall 2020: MATH 131A - Real Analysis
Summer 2020: MATH 151B - Applied Numerical Methods (II)
Spring 2020: MATH 151B - Applied Numerical Methods (II)
Winter 2020: MATH 151B - Applied Numerical Methods (II)
Spring 2019: MATH 151B - Applied Numerical Methods (II)
Fall 2018: MATH 151B - Applied Numerical Methods (II)
Spring 2018: MATH 151B - Applied Numerical Methods (II)
Winter 2018: MATH 170A - Probability Theory
Spring 2017: MATH 151A - Applied Numerical Methods (I)
Winter 2017: MATH 151A - Applied Numerical Methods (I)
