Noam Razin

Computer Science PhD Candidate

Tel Aviv University

I’m a PhD candidate in the School of Computer Science at Tel Aviv University, fortunate to be advised by Nadav Cohen.

My research interests broadly include the theoretical foundations and applications of machine learning. More specifically, I focus on mathematically analyzing aspects of deep learning (such as expressiveness, optimization, and generalization), with the goal of establishing theoretically backed practices.

My research is generously supported by the Apple Scholars in AI/ML and the Tel Aviv University Center for AI & Data Science PhD fellowships.

Email: noamrazin (at) mail.tau.ac.il

News

May 22: Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks accepted to ICML 2022.
Mar 22: Honored to receive the 2022 Apple Scholars in AI/ML PhD fellowship.
Jan 22: New paper analyzes implicit regularization in hierarchical tensor factorizations, which are equivalent to certain deep convolutional neural networks. Turns out it leads to a bias towards locality that can be countered using dedicated explicit regularization!
Oct 21: Honored to receive the Tel Aviv University Center for AI & Data Science excellence fellowship.
May 21: Implicit Regularization in Tensor Factorization accepted to ICML 2021. Check out this blog post for an overview.
Sep 20: Implicit Regularization in Deep Learning May Not Be Explainable by Norms accepted to NeurIPS 2020.
Nov 19: Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding accepted to AAAI 2020.

Publications

* denotes equal contribution.

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Noam Razin, Asaf Maman, Nadav Cohen

International Conference on Machine Learning (ICML), 2022

PDF Code

Implicit Regularization in Tensor Factorization

Noam Razin*, Asaf Maman*, Nadav Cohen

International Conference on Machine Learning (ICML), 2021

PDF Code Poster Video Blog

Implicit Regularization in Deep Learning May Not Be Explainable by Norms

Noam Razin, Nadav Cohen

Advances in Neural Information Processing Systems (NeurIPS), 2020

PDF Code Poster Blog

RecoBERT: A Catalog Language Model for Text-Based Recommendations

Itzik Malkiel, Oren Barkan, Avi Caciularu, Noam Razin, Ori Katz, Noam Koenigstein

Findings of the Association for Computational Linguistics: EMNLP, 2020

PDF

Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding

Oren Barkan*, Noam Razin*, Itzik Malkiel, Ori Katz, Avi Caciularu, Noam Koenigstein

AAAI Conference on Artificial Intelligence (AAAI), 2020

PDF Code Poster

Selected Talks

Implicit Regularization in Tensor Factorization
The Hebrew University Machine Learning Club, Jerusalem, Israel, June 2021
Video Slides
Implicit Regularization in Deep Learning May Not Be Explainable by Norms
Tel Aviv University Machine Learning Seminar, Tel Aviv, Israel, May 2020
Slides

Blog Posts

Implicit Regularization in Tensor Factorization: Can Tensor Rank Shed Light on Generalization in Deep Learning?, Off the Convex Path, July 21

Teaching

Teaching Assistant for Foundations of Deep Learning (course #0368-3080), Tel Aviv University, 2021 to present