Keskeiset käsitteet
(L0, L1)-smoothnessを考慮した非凸最適化における高速な確率的準ニュートン法の提案とその性能評価。
Tilastot
"Nevertheless, the studies of quasi-Newton methods are still lacking."
"Under this type of non-uniform smoothness, existing literature has designed stochastic first-order algorithms by utilizing gradient clipping techniques to obtain the optimal O(ǫ−3) sample complexity for finding an ǫ-approximate first-order stationary solution."
Lainaukset
"Classical convergence analyses for optimization algorithms rely on the widely adopted uniform smoothness assumption."
"Recent experimental evidence has revealed that the Lipschitz constant of the objective smoothness grows in the gradient norm along the training trajectory."