Bandit convex optimization

Bandit Convex Optimization (BCO) is a fundamental framework for decision making under uncertainty, which generalizes many problems from the realm of on- line and statistical learning.
In the bandit convex optimization setting, the player is only allowed to query function values of one point or two points, and the gradient information is not accessible as opposed to the full-information setting. In the following, we briefly discuss the progress of static regret minimization of the BCO problems.

Can a projection-free algorithm achieve a sublinear regret for bandit convex optimization?

In this paper, we propose the first computationally efficient projection-free algorithm for bandit convex optimization (BCO)

We show that our algorithm achieves a sublinear regret of O(nT4/5) (where T is the horizon and n is the dimension) for any bounded convex functions with uniformly bounded gradients

Is there an efficient algorithm for bandit linear optimization?

Competing in the dark: An efficient algorithm for bandit linear optimization

In Proceedings of the 21st Annual Conference on Learning Theory (COLT), 2008

Agarwal, O Dekel, and L Xiao

Optimal algorithms for online convex optimization with multi-point bandit feedback

What is bandit Online convex optimization?

Essentially, bandit online convex optimization is a gradient- of the game, the learner chooses a point xt from a known convex set X

Then, the adversary observes xt and chooses a convex loss function ft : X → R

After that, the loss function ft is revealed to the learner who suffers a loss ft(xt)

Bandit convex optimization (BCO) is a framework for on- line decision-making with limited feedback. In this frame- work, a player is given a convex feasible region K and the number T of rounds. In each round t = 1; 2; : : : ; T, the player chooses an action at 2 K, and the environ- ment independently chooses convex loss function ft : K ! [ 1; 1].

Categories

Bandit convex optimization algorithm
Convex optimization based method
Convex optimization calculator
Convex optimization. cambridge university press 2004
Difference between convex and plano convex lens
Convex lens is for
What is convex curvature
Convex lens problems
Convex optimization easy
Easy convex optimization problems
Difference between concave convex lens
Fast convex optimization algorithm
Convex lens position
Is lens concave or convex
Convex optimization zero duality gap
Convex curve example
Non convex optimization np hard
More convex vs less convex
Convex problem example
Convex set definition