.png){kind=icon}
.png){kind=icon}
Return
Bregman-Divergence-Based Arimoto-Blahut Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1109/TIT.2025.3597943.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We generalize the generalized Arimoto-Blahut algorithm to a general function defined over Bregman-divergence system. In existing methods, when linear constraints are imposed, each iteration needs to solve a convex minimization. Exploiting our obtained algorithm, we propose a minimization-free-iteration algorithm. This algorithm can be applied to classical and quantum rate-distortion theory. We numerically apply our method to the derivation of the optimal conditional distribution in the rate-distortion theory.
Keywords:
Minimization
Rate-distortion
Vectors
Mirrors
Convex functions
Quantum state
Mutual information
Probability distribution
Optimization
Machine learning algorithms
Bregman divergence
rate-distortion
em-algorithm
mixture family
convex-minimization-free
Journal
I
IF:
2.9
Papers:
317
Citations:
0