Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2003.10392
Cited By
v1
v2
v3
v4
v5 (latest)
Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting
23 March 2020
Lemeng Wu
Mao Ye
Qi Lei
Jason D. Lee
Qiang Liu
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"Steepest Descent Neural Architecture Optimization: Escaping Local Optimum with Signed Neural Splitting"
14 / 14 papers shown
Flat Channels to Infinity in Neural Loss Landscapes
Flavio Martinelli
Alexander Van Meegen
Berfin Simsek
W. Gerstner
Johanni Brea
300
2
0
17 Jun 2025
Learning Morphisms with Gauss-Newton Approximation for Growing Networks
Neal Lawton
Aram Galstyan
Greg Ver Steeg
205
0
0
07 Nov 2024
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
Neural Information Processing Systems (NeurIPS), 2024
Zhehao Huang
Xinwen Cheng
Jinghao Zheng
Haoran Wang
Zhengbao He
Tao Li
Xiaolin Huang
MU
247
26
0
29 Sep 2024
Beyond Uniform Scaling: Exploring Depth Heterogeneity in Neural Architectures
Akash Guna R.T
Arnav Chavan
Deepak Gupta
MDE
120
0
0
19 Feb 2024
Preparing Lessons for Progressive Training on Language Models
AAAI Conference on Artificial Intelligence (AAAI), 2024
Yu Pan
Ye Yuan
Yichun Yin
Jiaxin Shi
Zenglin Xu
Ming Zhang
Lifeng Shang
Xin Jiang
Qun Liu
263
13
0
17 Jan 2024
When To Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks
Haihang Wu
Wei Wang
T. Malepathirana
Damith A. Senanayake
D. Oetomo
Saman K. Halgamuge
197
2
0
06 Jan 2024
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
International Conference on Machine Learning (ICML), 2023
Anthony Chen
Huanrui Yang
Yulu Gan
Denis A. Gudovskiy
Zhen Dong
Haofan Wang
Tomoyuki Okuno
Yohei Nakata
Kurt Keutzer
Shanghang Zhang
213
4
0
14 Dec 2023
Reusing Pretrained Models by Multi-linear Operators for Efficient Training
Yu Pan
Ye Yuan
Yichun Yin
Zenglin Xu
Lifeng Shang
Xin Jiang
Qun Liu
248
17
0
16 Oct 2023
Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation
Neural Information Processing Systems (NeurIPS), 2023
Xin Yuan
Pedro H. P. Savarese
Michael Maire
164
5
0
22 Jun 2023
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training
International Conference on Learning Representations (ICLR), 2022
Tianlong Chen
Zhenyu Zhang
Pengju Wang
Santosh Balachandra
Haoyu Ma
Zehao Wang
Zinan Lin
OOD
AAML
353
52
0
20 Feb 2022
GradMax: Growing Neural Networks using Gradient Information
International Conference on Learning Representations (ICLR), 2022
Utku Evci
B. V. Merrienboer
Thomas Unterthiner
Max Vladymyrov
Fabian Pedregosa
302
65
0
13 Jan 2022
bert2BERT: Towards Reusable Pretrained Language Models
Cheng Chen
Yichun Yin
Lifeng Shang
Xin Jiang
Yujia Qin
Fengyu Wang
Zhi Wang
Xiao Chen
Zhiyuan Liu
Qun Liu
VLM
215
73
0
14 Oct 2021
Firefly Neural Architecture Descent: a General Approach for Growing Neural Networks
Neural Information Processing Systems (NeurIPS), 2021
Lemeng Wu
Bo Liu
Peter Stone
Qiang Liu
211
63
0
17 Feb 2021
Greedy Optimization Provably Wins the Lottery: Logarithmic Number of Winning Tickets is Enough
Neural Information Processing Systems (NeurIPS), 2020
Mao Ye
Lemeng Wu
Qiang Liu
136
17
0
29 Oct 2020
1
