An author says the new arXiv work includes exactly matching lower bounds for smooth convex minimization.
An author says their new arXiv work derives exact theory and minimax-optimal stepsizes for stochastic gradient descent's last iterate. For smooth convex minimization, they say its matching lower bounds prove no further progress is possible.
38
3 Sources, first seen ago
@prof_grimmerJust appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s last iterate. For smooth convex minimization, our theory comes with exactly matching lower bounds proving no further progress is possible.
@aaron_defazioRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…
@QuanquanGuRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@prof_grimmerJust appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s last iterate. For smooth convex minimization, our theory comes with exactly matching lower bounds proving no further progress is possible.@aaron_defazioRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@QuanquanGuRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@prof_grimmerJust appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s last iterate. For smooth convex minimization, our theory comes with exactly matching lower bounds proving no further progress is possible.@aaron_defazioRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@QuanquanGuRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@prof_grimmerJust appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s last iterate. For smooth convex minimization, our theory comes with exactly matching lower bounds proving no further progress is possible.@aaron_defazioRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…@QuanquanGuRT @prof_grimmer: Just appeared on arXiv, we derived exact theory and minimax optimal stepsizes for Stochastic Gradient Descent (SGD)'s las…—
Not ranked yet
—
Not ranked yet
