Improved Regret Bounds for Projection-free Bandit Convex Optimization

10/08/2019
by   Dan Garber, et al.
0

We revisit the challenge of designing online algorithms for the bandit convex optimization problem (BCO) which are also scalable to high dimensional problems. Hence, we consider algorithms that are projection-free, i.e., based on the conditional gradient method whose only access to the feasible decision set, is through a linear optimization oracle (as opposed to other methods which require potentially much more computationally-expensive subprocedures, such as computing Euclidean projections). We present the first such algorithm that attains O(T^3/4) expected regret using only O(T) overall calls to the linear optimization oracle, in expectation, where T is the number of prediction rounds. This improves over the O(T^4/5) expected regret bound recently obtained by <cit.>, and actually matches the current best regret bound for projection-free online learning in the full information setting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/09/2022

New Projection-free Algorithms for Online Convex Optimization with Adaptive Regret Guarantees

We present new efficient projection-free algorithms for online convex op...
research
05/23/2022

Exploiting the Curvature of Feasible Sets for Faster Projection-Free Online Learning

In this paper, we develop new efficient projection-free algorithms for O...
research
12/22/2020

Projection-Free Bandit Optimization with Privacy Guarantees

We design differentially private algorithms for the bandit convex optimi...
research
02/09/2023

Projection-free Online Exp-concave Optimization

We consider the setting of online convex optimization (OCO) with exp-con...
research
01/30/2020

Faster Projection-free Online Learning

In many online learning problems the computational bottleneck for gradie...
research
10/15/2020

Revisiting Projection-free Online Learning: the Strongly Convex Case

Projection-free optimization algorithms, which are mostly based on the c...
research
05/18/2018

Projection-Free Bandit Convex Optimization

In this paper, we propose the first computationally efficient projection...

Please sign up or login with your details

Forgot password? Click here to reset