Diyuan Wu
Graduate School
Mondelli Group
2 Publications
2024 | Published | Conference Paper | IST-REx-ID: 19518 |

The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
[Preprint]
View
| Download Preprint (ext.)
| arXiv
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
2023 | Published | Conference Paper | IST-REx-ID: 14924 |

Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.
Grants
2 Publications
2024 | Published | Conference Paper | IST-REx-ID: 19518 |

The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
[Preprint]
View
| Download Preprint (ext.)
| arXiv
Wu, Diyuan, The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information. 38th Conference on Neural Information Processing Systems 37. 2024
2023 | Published | Conference Paper | IST-REx-ID: 14924 |

Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.
[Published Version]
View
| Download Published Version (ext.)
| arXiv
D. Wu, V. Kungurtsev, M. Mondelli, in:, Transactions on Machine Learning Research, ML Research Press, 2023.