scholarly journals Optimal No-Regret Learning in Strongly Monotone Games with Bandit Feedback

2021 ◽  
Author(s):  
Tianyi Lin ◽  
Zhengyuan Zhou ◽  
Wenjia Ba ◽  
Jiawei Zhang
Keyword(s):  
1997 ◽  
Vol 66 ◽  
pp. 269-274 ◽  
Author(s):  
Wolfgang Walter
Keyword(s):  

2013 ◽  
Vol 2013 ◽  
pp. 1-7
Author(s):  
Bin-Chao Deng ◽  
Tong Chen

LetHbe a real Hilbert space. LetT1,T2:H→Hbek1-,k2-strictly pseudononspreading mappings; letαnandβnbe two real sequences in (0,1). For givenx0∈H, the sequencexnis generated iteratively byxn+1=βnxn+1-βnTw1αnγfxn+I-μαnBTw2xn,∀n∈N, whereTwi=1−wiI+wiTiwithi=1,2andB:H→His strongly monotone and Lipschitzian. Under some mild conditions on parametersαnandβn, we prove that the sequencexnconverges strongly to the setFixT1∩FixT2of fixed points of a pair of strictly pseudononspreading mappingsT1andT2.


Sign in / Sign up

Export Citation Format

Share Document