Scholar
Yehuda Dar
Google Scholar ID: lKeL2F4AAAAJ
Assistant Professor of Computer Science, Ben-Gurion University
Citations & Impact
Citations
434
H-index
10
i10-index
11
Publications
20
Co-authors
11
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Publications:
- - "A Farewell to the Bias-Variance Tradeoff? An Overview of the Theory of Overparameterized Machine Learning" (arXiv:2109.02355)
- - "Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective" (arXiv:2510.03151)
- - "How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?" (arXiv:2503.08633)
- - "TL-PCA: Transfer Learning of Principal Component Analysis" (arXiv:2410.10805)
- - "How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks" (arXiv:2405.17377)
- - "How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation" (ECML 2024)
- - "The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression" (SIAM Journal on Mathematics of Data Science, 2024)
- - "Double Double Descent: On Generalization Errors in Transfer Learning between Linear Regression Tasks" (SIAM Journal on Mathematics of Data Science, 2022)
- - "Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors" (ICML 2020)
- - "Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective" (CVPR 2022)
- - "Frozen Overparameterization: A Double Descent Perspective on Transfer Learning of Deep Neural Networks" (arXiv:2211.11074)
- - "Double Descent and Other Interpolation Phenomena in GANs" (arXiv)
Research Experience
- Postdoctoral fellow: Computer Science Department at the Technion
- Postdoctoral research associate: Department of Electrical and Computer Engineering at Rice University, worked with Prof. Richard Baraniuk
- Organizer: 2021 and 2022 Workshop on the Theory of Overparameterized Machine Learning (TOPML)
- Area chair: NeurIPS 2024, 2025 and ICML 2025
Education
- BSc: Technion — Israel Institute of Technology, Computer Engineering
- MSc: Technion — Israel Institute of Technology, Electrical Engineering
- PhD: Technion — Israel Institute of Technology, Computer Science, supervised by Prof. Alfred Bruckstein and Prof. Michael Elad
Background
- Research Interests: Foundations of machine and deep learning
- Field: Computer Science
- Summary: Senior lecturer (assistant professor) in the Computer Science Department at Ben-Gurion University, focusing on foundational research in overparameterized machine learning.
