On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization

@inproceedings{Shamir2013OnTC,
  title={On the Complexity of Bandit and Derivative-Free Stochastic Convex Optimization},
  author={Ohad Shamir},
  booktitle={COLT},
  year={2013}
}
The problem of stochastic convex optimization with bandit feedback (in the learning community) or without knowledge of gradients (in the optimization community) has received much attention in recent years, in the form of algorithms and performance upper bounds. However, much less is known about the inherent complexity of these problems, and there are few lower bounds in the literature, especially for nonlinear functions. In this paper, we investigate the attainable error/regret in the bandit… CONTINUE READING
Highly Cited
This paper has 59 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 42 extracted citations

Regret Analysis for Continuous Dueling Bandit

NIPS • 2017
View 7 Excerpts
Highly Influenced

Bandit Convex Optimization: Towards Tight Bounds

NIPS • 2014
View 3 Excerpts
Highly Influenced

60 Citations

01020'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 60 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Problem Complexity and Method

A. Nemirovsky, D. Yudin
Efficiency in Optimization. Wiley-Interscience, • 1983
View 10 Excerpts
Highly Influenced

Regret analysis of stochastic and nonstochastic multi - armed bandit problems

N. Cesa-Bianchi Bubeck, S. Kakade
2012

Optimization of convex functions with random pursuit

S. Stich, C. Müller, B. Gärtner
CoRR, abs/1111.0194, • 2011

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

O. Dekel Agarwal, L. Xiao
In COLT • 2010

Similar Papers

Loading similar papers…