New accelerated Bregman proximal gradient algorithms with inexact oracles achieve O(1/N^2)-type rates for relatively smooth problems, with an adaptive intermediate variant interpolating between fast and robust rates.
Lectures on convex optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Accelerated Bregman gradient methods for relatively smooth and relatively Lipschitz continuous minimization problems
New accelerated Bregman proximal gradient algorithms with inexact oracles achieve O(1/N^2)-type rates for relatively smooth problems, with an adaptive intermediate variant interpolating between fast and robust rates.