| Implicit bias of gradient descent for mean squared error regression with wide neural networks H Jin, G Montúfar Journal of Machine Learning Research 24, 1--97, 2023 | 49 | 2023 |
| Learning curves for Gaussian process regression with power-law priors and targets H Jin, PK Banerjee, G Montúfar The Tenth International Conference on Learning Representations (ICLR 2022), 2022 | 16 | 2022 |
| Characterizing the Spectrum of the NTK via a Power Series Expansion M Murray, H Jin, B Bowman, G Montufar The Eleventh International Conference on Learning Representations (ICLR 2023)., 2023 | 13 | 2023 |
| Noisy Subgraph Isomorphisms on Multiplex Networks H Jin, X He, Y Wang, H Li, AL Bertozzi 2019 IEEE International Conference on Big Data (Big Data), 4899-4905, 2019 | 11 | 2019 |
| Process-driven autoformalization in lean 4 J Lu, Y Wan, Z Liu, Y Huang, J Xiong, C Liu, J Shen, H Jin, J Zhang, ... arXiv preprint arXiv:2406.01940, 2024 | 6 | 2024 |
| Towards understanding how transformer perform multi-step reasoning with matching operation Z Wang, Y Wang, Z Zhang, Z Zhou, H Jin, T Hu, J Sun, Z Li, Y Zhang, ... arXiv preprint arXiv:2405.15302, 2024 | 5 | 2024 |
| How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training Y Ou, Y Yao, N Zhang, H Jin, J Sun, S Deng, Z Li, H Chen arXiv preprint arXiv:2502.11196, 2025 | | 2025 |
| CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search XW Yang, Z Zhou, H Wang, A Li, WD Wei, H Jin, Z Li, YF Li The Thirteenth International Conference on Learning Representations (ICLR 2025), 2025 | | 2025 |
| Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers BK Chen, T Hu, H Jin, HK Lee, K Kawaguchi The Forty-First International Conference on Machine Learning (ICML 2024), 2024 | | 2024 |
| Generalization of Wide Neural Networks from the Perspective of Linearization and Kernel Learning H Jin University of California, Los Angeles, 2022 | | 2022 |
Guido F. MontufarUCLA, Mathematics and Statistics & Data Science, Max Planck Institute MiSВерификована је имејл адреса на math.ucla.edu