No confident code implementation found for this paper.
We introduce a simple and efficient algorithm for unconstrained zeroth-order stochastic convex bandits and prove its regret is at most $(1 + r/d)[d^{1.5} \sqrt{n} + d^3] polylog(n, d, r)$ where $n$ is the horizon, $d$ the dimension and $r$ is the radius of a known ball containing the minimiser of the loss.
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
Online Newton Method for Bandit Convex Optimisation
Bandit Convex Optimisation
Bandit Convex Optimisation Revisited: FTRL Achieves $\tilde{O}(t^{1/2})$ Regret
Accelerated zero-order SGD under high-order smoothness and overparameterized regime
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
A Parameter-Free and Near-Optimal Zeroth-Order Algorithm for Stochastic Convex Optimization
@article{lattimore2023secondorder,
title = {A Second-Order Method for Stochastic Bandit Convex Optimisation},
author = {Tor Lattimore and András György},
year = {2023},
eprint = {2302.05371},
archivePrefix = {arXiv},
url = {http://arxiv.org/abs/2302.05371v1}
}Shows whether official code is linked for this paper.
[](https://codeofpaper.com/paper/2302.05371)