Second-order Pruning
Second-Order Pruning is a systematic pruning methodology that selectively removes model parameters based on second-order sensitivity measures, distinguishing itself from first-order methods by incorporating curvature information of the loss function to preserve performance with higher structural precision.
4
Publications
98
Citations
14
Authors
8
Institutions
Publications per year
2017–2026
2
Parents
4
VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores
Roberto L. Castro, Andrei Ivanov, Diego Andrade et al. · 2023 · 20 citations · Full text
Giovanni Lombardo, Harald Uhlig · International Economic Review · 2018 · 12 citations · Full text
1–5 of 4
14
1
h-index
1
h-index
1
h-index
1
h-index
Nanjing University of Aeronautics and Astronautics, China
1 publications · 19 citations
1
h-index
1–5 of 14
8

Peking University
Beijing, China
1 h-index
1 publications
41 citations

University of Surrey
Guildford, United Kingdom
1 h-index
2 publications
52 citations
Nanjing University of Science and Technology
Nanjing, China
1 h-index
2 publications
38 citations
University of Chicago
Chicago, United States
1 h-index
1 publications
12 citations
ZTE (China)
Shenzhen, China
1 h-index
1 publications
19 citations
Bank for International Settlements
Basel, Switzerland
1 h-index
1 publications
12 citations
ZTE (United States)
Richardson, United States
1 h-index
1 publications
19 citations
University of California, Berkeley
Berkeley, United States
1 h-index
6 publications
246 citations
1–8 of 8
1 publications · 12 citations
1
h-index
1 publications · 19 citations
1
h-index
1 publications · 26 citations
1
h-index
Conference · 1 publications · 41 citations
1
h-index
Repository · 1 publications · 10 citations
1–5