Documentation

FirstOrderMethodsOptimization_Beck_2017.Chap11.Theorem_11_13

theorem IsBlockProximalGradientProblem.randomized_block_proximal_gradient_iterate_mem_effective_domain {ι : Type u} [Fintype ι] {Ei : ιType v} [(i : ι) → NormedAddCommGroup (Ei i)] [(i : ι) → InnerProductSpace (Ei i)] [∀ (i : ι), ProperSpace (Ei i)] {Li : ιPosReal} {f : ((i : ι) → Ei i)EReal} {g : (i : ι) → Ei iEReal} {block_gradient : (i : ι) → ((j : ι) → Ei j)Ei i} {XStar : Set ((i : ι) → Ei i)} {FOpt : } (hproblem : IsBlockProximalGradientProblem f g block_gradient XStar FOpt Li) (x0 : (effective_domain (separableSum g))) (sampled_block : ι) (k : ) :

Every realized RBPG iterate remains in the effective domain of the block-separable regularizer, provided the initial point does.

theorem RandomizedBlockProximalGradientAssumptions.randomized_block_proximal_gradient_sufficient_decrease {ι : Type u} [Fintype ι] {Ei : ιType v} [(i : ι) → NormedAddCommGroup (Ei i)] [(i : ι) → InnerProductSpace (Ei i)] [∀ (i : ι), ProperSpace (Ei i)] {Li : ιPosReal} {f : ((i : ι) → Ei i)EReal} {g : (i : ι) → Ei iEReal} {block_gradient : (i : ι) → ((j : ι) → Ei j)Ei i} {XStar : Set ((i : ι) → Ei i)} {FOpt : } (hproblem : RandomizedBlockProximalGradientAssumptions f g block_gradient XStar FOpt Li) (x0 : (effective_domain (separableSum g))) (sampled_block : ι) (k : ) :
composite_model_objective f (separableSum g) (randomized_block_proximal_gradient_method (↑(.interior_effective_domain_point x0)) sampled_block k) - composite_model_objective f (separableSum g) (randomized_block_proximal_gradient_method (↑(.interior_effective_domain_point x0)) sampled_block (k + 1)) (1 / (2 * (Li (sampled_block k))) * .gradient_mapping (Li (sampled_block k)) (sampled_block k) (randomized_block_proximal_gradient_method (↑(.interior_effective_domain_point x0)) sampled_block k) ^ 2)

Theorem 11.13: along any realized RBPG sample path, each step decreases the composite objective by at least (1 / (2 L_{i_k})) ‖G^{i_k}_{L_{i_k}}(x^k)‖^2.