Under a new scaled Kurdyka-Łojasiewicz property, Bregman projected gradient with the Shannon entropy kernel converges to critical points for continuous subanalytic objectives, with linear rates when the scaled exponent is 1/2.
The rate of convergence of Bregman proximal methods: Local geometry versus regularity versus sharpness.SIAM Journal on Optimization, 34(3):2440–2471, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
On the Iterate Convergence of Bregman Projected Gradient Method
Under a new scaled Kurdyka-Łojasiewicz property, Bregman projected gradient with the Shannon entropy kernel converges to critical points for continuous subanalytic objectives, with linear rates when the scaled exponent is 1/2.