Profiles2021-2022
Decebal Constantin Mocanu
Eindhoven University of Technology
5Papers
4Last author
9Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers5
- The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse TrainingAuthor 5 of 7ICLR 2022 · 141 citations
- Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic SparsityAuthor 9 of 9ICLR 2022 · 62 citations
- Dynamic Sparse Network for Time Series Classification: Learning What to "See"Author 7 of 7NeurIPS 2022 · 45 citations
- Where to Pay Attention in Sparse Training for Feature Selection?Author 4 of 4NeurIPS 2022 · 25 citations
- Sparse Training via Boosting Pruning Plasticity with NeuroregenerationAuthor 10 of 10NeurIPS 2021 · 145 citations
