We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| fxrshed/root-newton | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| newton_search | Ran | fxrshed/root-newton/methods.py pointer only (licence: NONE) · get_code("4c5123bfacfa72d5") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper investigates the global convergence of stepsized Newton methods for convex functions with Hölder continuous Hessians or third derivatives. We propose several simple stepsize schedules with fast global convergence guarantees, up to $\mathcal {O}\left(k^{-3} \right)$. For cases with multiple plausible smoothness parameterizations or an unknown smoothness constant, we introduce a stepsize linesearch and a backtracking procedure with provable convergence as if the optimal smoothness parameters were known in advance. Additionally, we present strong convergence guarantees for the practically popular Newton method with exact linesearch.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2405.18926")
get_code_for_paper("2405.18926")
have("2405.18926")
Connect an agent — have() is free.