| Implicit Regularization in Deep Learning May Not Be Explainable by Norms N Razin, N Cohen Advances in Neural Information Processing Systems 34 (NeurIPS), 2020 | 170 | 2020 |
| What Algorithms Can Transformers Learn? A Study in Length Generalization H Zhou, A Bradley, E Littwin, N Razin, O Saremi, J Susskind, S Bengio, ... 12th International Conference on Learning Representations (ICLR), 2024 | 60 | 2024 |
| Implicit Regularization in Tensor Factorization N Razin, A Maman, N Cohen Proceedings of the 38th International Conference on Machine Learning (ICML), 2021 | 51 | 2021 |
| Scalable Attentive Sentence-Pair Modeling via Distilled Sentence Embedding O Barkan, N Razin, I Malkiel, O Katz, A Caciularu, N Koenigstein The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2019 | 40 | 2019 |
| Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks N Razin, A Maman, N Cohen Proceedings of the 39th International Conference on Machine Learning (ICML), 2022 | 30 | 2022 |
| RecoBERT: A Catalog Language Model for Text-Based Recommendations I Malkiel, O Barkan, A Caciularu, N Razin, O Katz, N Koenigstein Findings of the Association for Computational Linguistics: EMNLP, 2020 | 30 | 2020 |
| On the Ability of Graph Neural Networks to Model Interactions Between Vertices N Razin, T Verbin, N Cohen Advances in Neural Information Processing Systems 37 (NeurIPS), 2023 | 8 | 2023 |
| Sentence similarity scoring using neural network distillation O Barkan, N Razin, N Koenigstein US Patent App. 16/789,385, 2021 | 7 | 2021 |
| What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement Y Alexander, N De La Vega, N Razin, N Cohen Advances in Neural Information Processing Systems 37 (NeurIPS), 2023 | 6* | 2023 |
| Vanishing Gradients in Reinforcement Finetuning of Language Models N Razin, H Zhou, O Saremi, V Thilak, A Bradley, P Nakkiran, J Susskind, ... 12th International Conference on Learning Representations (ICLR), 2024 | 4 | 2024 |
| Machine learning multiple features of depicted item O Barkan, N Razin, N Koenigstein, R Hirsch, N Nice US Patent 11,373,095, 2022 | 3 | 2022 |
| Searching using changed feature of viewed item O Barkan, N Razin, R Hirsch, N Koenigstein, N Nice US Patent App. 16/725,461, 2021 | 2 | 2021 |
| Understanding Deep Learning via Notions of Rank N Razin arXiv preprint arXiv:2408.02111, 2024 | 1 | 2024 |
| Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States N Razin, Y Alexander, E Cohen-Karlik, R Giryes, A Globerson, N Cohen Proceedings of the 41st International Conference on Machine Learning (ICML), 2024 | 1 | 2024 |
| Lecture Notes on Linear Neural Networks: A Tale of Optimization and Generalization in Deep Learning N Cohen, N Razin arXiv preprint arXiv:2408.13767, 2024 | | 2024 |
Nadav CohenAsst. Professor of Computer Science, Tel Aviv University | CTO & Co-Founder, ImubitVerified email at tauex.tau.ac.il
