Statements
Source excerpts; proofs omitted. recall restates an existing declaration; #check records an expression, not its inferred type.
Definition 12.1: the primal objective for the dual-based proximal-gradient model is the
Chapter 10 composite objective specialized to f and g ∘ A.
recall composite_model_objective
Source context
universe u v
open Set
variable {E : Type u} {Y : Type v}recall composite_model_objective_apply
Source context
universe u v
open Set
variable {E : Type u} {Y : Type v}noncomputable def
dual_based_proximal_gradient_primal_optimal_value
{E : Type u}
{Y : Type v}
(f : E → EReal)
(g : Y → EReal)
(A : E → Y)
:
EReal
The optimal value f_opt of the dual-based primal model is the infimum of the range of the
primal objective x ↦ f x + g (A x).
Instances For
@[simp]
theorem
dual_based_proximal_gradient_primal_optimal_value_eq_sInf
{E : Type u}
{Y : Type v}
(f : E → EReal)
(g : Y → EReal)
(A : E → Y)
:
dual_based_proximal_gradient_primal_optimal_value f g A = sInf (Set.range (composite_model_objective f (g ∘ A)))
Expanding the primal optimal value gives the infimum of the attained objective values.