Meta-initialization
Meta-Initialization is a meta-learning strategy that establishes an optimal starting point in parameter space for rapid adaptation to new tasks by encoding prior knowledge across related learning episodes.
49
Publications
3.7K
Citations
210
Authors
67
Institutions
Publications per year
2017–2026
46
Parents
49
Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
Zhenguo Li, Fengwei Zhou, Fei Chen et al. · arXiv (Cornell University) · 2017 · 845 citations · Full text
On First-Order Meta-Learning Algorithms
Alex Nichol, Joshua Achiam, John Schulman · arXiv (Cornell University) · 2018 · 544 citations · Full text
Learned Initializations for Optimizing Coordinate-Based Neural Representations
Matthew Tancik, Ben Mildenhall, Terrance Wang et al. · 2021 · 217 citations
1–5 of 49
210
3
h-index
3
h-index
3
h-index
2
h-index
2
h-index
1–5 of 210
67
Google (United States)
Mountain View, United States
4 h-index
16 publications
2.6K citations
GlaxoSmithKline (Netherlands)
Zeist, Netherlands
3 h-index
3 publications
44 citations
University of Chinese Academy of Sciences
Beijing, China
2 h-index
3 publications
328 citations
The Ohio State University
Columbus, United States
2 h-index
3 publications
66 citations
Korea Advanced Institute of Science and Technology
Daejeon, South Korea
2 h-index
5 publications
305 citations
Seoul National University
Seoul, South Korea
2 h-index
10 publications
390 citations
Nanjing University
Nanjing, China
2 h-index
4 publications
154 citations

Xi'an Jiaotong University
Xi'an, China
1 h-index
1 publications
155 citations
1–8 of 67
Repository · 15 publications · 1.8K citations
13
h-index
Conference · 2 publications · 75 citations
2
h-index
Repository · 2 publications · 24 citations
2
h-index
TPAMI · 2 publications · 128 citations
2
h-index
1 publications · 78 citations
1
h-index
1–5