Optimization Induced Equilibrium Networks: An Explicit Optimization Perspective for Understanding Equilibrium Models-Reference-Cited by-同舟云学术

Optimization Induced Equilibrium Networks: An Explicit Optimization Perspective for Understanding Equilibrium Models

Author:

Xie Xingyu¹^ORCID,Wang Qiuhao¹,Ling Zenan¹^ORCID,Li Xia²,Liu Guangcan³^ORCID,Lin Zhouchen¹^ORCID

Affiliation:

1. Key Laboratory of Machine Perception (MOE), School of Artificial Intelligence, Peking University, Beijing, China

2. Swiss Federal Institute of Technology, Zürich, Switzerland

3. School of Automation, Southeast University, Nanjing, China

Funder

New Generation AI Major Project of Ministry of Science and Technology of China

National Natural Science Foundation of China

PCL

NSF China

NSFC Tianyuan Fund for Mathematics

PKU-Baidu Fund

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference49 articles.

1. Joint inference and input optimization in equilibrium networks;gurumurthy;Proc Adv Neural Inf Process Syst,2021

2. Fixed point networks: Implicit depth models with jacobian-free backprop;fung,2021

3. Efficient multiple hyperparameter learning for log-linear models;do;Proc Adv Neural Inf Process Syst,2007

4. On the theory of implicit deep learning: Global convergence with implicit layers;kawaguchi,2021

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献