Diyuan Wu

3 Publications

Mark all

[3]
2025 | Published | Conference Paper | IST-REx-ID: 21326 | OA
D. Wu and M. Mondelli, “Neural collapse beyond the unconstrained features model: Landscape, dynamics, and generalization in the mean-field regime,” in Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025, vol. 267, pp. 67499–67536.
[Published Version] View | Files available | arXiv
 
[2]
2024 | Published | Conference Paper | IST-REx-ID: 19518 | OA
D. Wu, I.-V. Modoranu, M. Safaryan, D. Kuznedelev, and D.-A. Alistarh, “The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information,” in 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[1]
2023 | Published | Conference Paper | IST-REx-ID: 14924 | OA
D. Wu, V. Kungurtsev, and M. Mondelli, “Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence,” in Transactions on Machine Learning Research, 2023.
[Published Version] View | Download Published Version (ext.) | arXiv
 
Marked Publication(s)

Search

Filter Publications

Display / Sort

Citation Style: IEEE

Export / Embed

Grants


3 Publications

Mark all

[3]
2025 | Published | Conference Paper | IST-REx-ID: 21326 | OA
D. Wu and M. Mondelli, “Neural collapse beyond the unconstrained features model: Landscape, dynamics, and generalization in the mean-field regime,” in Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada, 2025, vol. 267, pp. 67499–67536.
[Published Version] View | Files available | arXiv
 
[2]
2024 | Published | Conference Paper | IST-REx-ID: 19518 | OA
D. Wu, I.-V. Modoranu, M. Safaryan, D. Kuznedelev, and D.-A. Alistarh, “The iterative optimal brain surgeon: Faster sparse recovery by leveraging second-order information,” in 38th Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, vol. 37.
[Preprint] View | Download Preprint (ext.) | arXiv
 
[1]
2023 | Published | Conference Paper | IST-REx-ID: 14924 | OA
D. Wu, V. Kungurtsev, and M. Mondelli, “Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence,” in Transactions on Machine Learning Research, 2023.
[Published Version] View | Download Published Version (ext.) | arXiv
 
Marked Publication(s)

Search

Filter Publications

Display / Sort

Citation Style: IEEE

Export / Embed