Develops a Bregman proximal gradient method with entropic Legendre functions for linear optimization under entropic constraints, establishing O(1/n) convergence and justifying the Blahut-Arimoto algorithm for specific cost structures.
IEEE Transactions on Information Theory 56(9), 4181–4206 (2010)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bregman proximal gradient method for linear optimization under entropic constraints
Develops a Bregman proximal gradient method with entropic Legendre functions for linear optimization under entropic constraints, establishing O(1/n) convergence and justifying the Blahut-Arimoto algorithm for specific cost structures.