Research output per year
Research output per year
Personal profile
Quote
Shiwei Liu is a Ph.D. candidate in the Mathematics and Computer Science department at the Eindhoven University of Technology (TU/e). He is an expert in deep learning and sparse neural networks. Recently, his research interest is designing empirical studies to understand the behaviors of neural networks. He believes that sparse artificial neural networks have the potential to fully replace conventional dense neural networks and it's just a matter of time.
Fingerprint
Dive into the research topics where Shiwei Liu is active. These topic labels come from the works of this person. Together they form a unique fingerprint.
- 1 Similar Profiles
Network
Recent external collaboration on country/territory level. Dive into details by clicking on the dots or
Research output
-
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity
Liu, S., Chen, T., Atashgahi, Z., Chen, X., Sokar, G., Mocanu, E., Pechenizkiy, M., Wang, Z. & Mocanu, D. C., 20 Jan 2022, (Accepted/In press) International Conference on Learning Representations, ICLR 2022.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
File3 Downloads (Pure) -
Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance
Liu, S., Tian, Y., Chen, T. & Shen, L., 1 Mar 2022, (Submitted) In: International Journal of Computer Vision. XX, XResearch output: Contribution to journal › Article › Academic › peer-review
-
Sparse Neural Network Training with In-Time Over-Parameterization
Liu, S., 6 Apr 2022, Eindhoven: Eindhoven University of Technology. 154 p.Research output: Thesis › Phd Thesis 1 (Research TU/e / Graduation TU/e)
Open AccessFile102 Downloads (Pure) -
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training
Liu, S., Chen, T., Chen, X., Shen, L., Mocanu, D. C., Wang, Z. & Pechenizkiy, M., 20 Jan 2022, (Accepted/In press) International Conference on Learning Representations, ICLR 2022.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
File3 Downloads (Pure) -
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Liu, S., Yin, L., Mocanu, D. C. & Pechenizkiy, M., 18 Jul 2021, Proceedings of the 38th International Conference on Machine Learning (ICML2021). Meila, M. & Zhang, T. (eds.). p. 6989-7000 (Proceedings of Machine Learning Research; vol. 139).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
Open Access
Prizes
Activities
- 1 Conference
-
2020 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2020)
Shiwei Liu (Organiser)
13 Sep 2020 → 18 Sep 2020Activity: Participating in or organising an event types › Conference › Scientific