Near-optimal method for highly smooth convex optimization
We propose a near-optimal method for highly smooth convex optimization. More precisely,
in the oracle model where one obtains the $ p^{th} $ order Taylor expansion of a function at
the query point, we propose a method with rate of convergence $\tilde {O}(1/k^{\frac {3p+
1}{2}}) $ after $ k $ queries to the oracle for any convex function whose $ p^{th} $ order
derivative is Lipschitz.
in the oracle model where one obtains the $ p^{th} $ order Taylor expansion of a function at
the query point, we propose a method with rate of convergence $\tilde {O}(1/k^{\frac {3p+
1}{2}}) $ after $ k $ queries to the oracle for any convex function whose $ p^{th} $ order
derivative is Lipschitz.
Abstract
We propose a near-optimal method for highly smooth convex optimization. More precisely, in the oracle model where one obtains the order Taylor expansion of a function at the query point, we propose a method with rate of convergence after queries to the oracle for any convex function whose order derivative is Lipschitz.
proceedings.mlr.press
Showing the best result for this search. See all results