Ziv Goldfeld | Cornell Engineering

Biography

Ziv Goldfeld joined the School of Electrical and Computer Engineering at Cornell University as an Assistant Professor in July 2019. He is a graduate field member of Computer Science, Statistics and Data Science, Operations Research and Information Engineering, and the Center of Applied Mathematics at Cornell University. He is also a member of the Foundations of Information, Networks, and Decision Systems (FIND) group. During the 2017-2019 academic years, he was a postdoctoral research fellow in LIDS of the Electrical Engineering and Computer Science Department at MIT. Before that, Goldfeld received his B.Sc., M.Sc. (both summa cum laude) and Ph.D. in the Department of Electrical and Computer Engineering at Ben Gurion University of the Negev. Honors include the NSF CAREER Award, the IBM University Award, the Michael Tien ’72 Excellence in Teaching Award, and the Rothschild postdoctoral fellowship.

Research Interests

Goldfeld’s research aims to develop theoretical foundations for learning algorithms that are provably accurate, efficient, scalable, robust, and private. To model a variety of learning tasks holistically, he employs a flexible mathematical framework based on statistical divergences and information measures. Through this lens, many learning tasks can be abstractly viewed as operations in a suitable geometry on probability distributions over high-dimensional manifolds. Goldfeld studies fundamental aspects of learning and inference from this perspective, integrating ideas from optimal transport theory, information theory, mathematical statistics, optimization, and applied probability. This interdisciplinary approach often reveals new connections that foster cross-field fertilization.

Artificial Intelligence
Statistics and Machine Learning
Information, Networks, and Decision Systems
Information Theory and Communications

Teaching Interests

ECE 3200/5200 Foundations of Machine Learning
ECE 4110 Random Signals in Communications and Signal Processing
ECE 6630 Information Theory for Data Transmission, Security and Machine Learning
ECE 6970 Optimal transport theory and statistical divergences: from foundations to modern applications

Select Publications

R. Sadhu, Z. Goldfeld, and K. Kato, “Stability and statistical inference for semidiscrete optimal transport maps”, Annals of Applied Probability, December 2024.
G. Rioux, Z. Goldfeld, and K. Kato, “Entropic Gromov-Wasserstein distances: stability and algorithms”, Journal of Machine Learning Research, October 2024.
S. Nietert, Z. Goldfeld, and S. Shafiee, “Robust estimation under local and global adversarial corruptions”, Conference on Learning Theory (COLT), June-July 2024.
Z. Zhang, Z. Goldfeld, Y. Mroueh, and B. K. Sriperumbudur, “Gromov-Wasserstein distances: entropic regularization, duality, and sample complexity”, Annals of Statistics, May 2024.
Z. Goldfeld, D. Patel, S. Sreekumar, and M. Wilde, “Quantum neural estimation of entropies”, Physical Review A, March 2024.

Ziv Goldfeld's Google Scholar

Select Awards and Honors

Michael Tien ’72 Excellence in Teaching Award 2023
NSF CAREER Award, National Science Foundation 2021
NSF CRII Award, National Science Foundation 2020
IBM University Award 2020
The Rothschild Postdoctoral Fellowship 2017

Education

B.S., Electrical and Computer Engineering, Ben Gurion University of the Negev 2012
M.S., Electrical and Computer Engineering, Ben Gurion University of the Negev 2012
Ph.D., M.Sc. Electrical and Computer Engineering, Ben Gurion University of the Negev 2018
Postdoctoral fellow, Laboratory for Information and Decision Systems (LIDS), Electrical Engineering and Computer Science, MIT 2019