Parameter-free first-order gradient minimization in ℓp geometry
Statement
Fix and let . Given a first-order local value--gradient oracle for an objective whose gradient is -Lipschitz from to , an initial point with a solution satisfying , and a target , determine whether there is a parameter-free algorithm that does not know , , or and returns a queried point satisfying , with dimension-free oracle complexity governed by . Under a nondegenerate secant initialization, the claimed bounds are post-initialization queries for and for , together with an additive calibration cost .
Record
- Added
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.