Parametric majorizers replace a bi-level training problem with single-level surrogate losses that upper-bound the original objective, enabling efficient learning of energy-based models.
Insights Into Analysis Operator Learning: From Patch-Based Sparse Models to Higher Order MRFs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Parametric Majorization for Data-Driven Energy Minimization Methods
Parametric majorizers replace a bi-level training problem with single-level surrogate losses that upper-bound the original objective, enabling efficient learning of energy-based models.