Corpus ID: 229349126

Projection-Free Bandit Optimization with Privacy Guarantees

@inproceedings{Ene2021ProjectionFreeBO,
  title={Projection-Free Bandit Optimization with Privacy Guarantees},
  author={Alina Ene and Huy L. Nguyen and Adrian Vladu},
  booktitle={AAAI},
  year={2021}
}
We design differentially private algorithms for the bandit convex optimization problem in the projection-free setting. This setting is important whenever the decision set has a complex geometry, and access to it is done efficiently only through a linear optimization oracle, hence Euclidean projections are unavailable (e.g. matroid polytope, submodular base polytope). This is the first differentially-private algorithm for projection-free bandit optimization, and in fact our bound of Õ(T… Expand
Littlestone Classes are Privately Online Learnable

References

SHOWING 1-10 OF 41 REFERENCES
Improved Regret Bounds for Projection-free Bandit Convex Optimization
Projection-Free Bandit Convex Optimization
Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds
Playing Non-linear Games with Linear Oracles
  • D. Garber, Elad Hazan
  • Mathematics, Computer Science
  • 2013 IEEE 54th Annual Symposium on Foundations of Computer Science
  • 2013
Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback
Robbing the bandit: less regret in online geometric optimization against an adaptive adversary
The Price of Bandit Information for Online Optimization
Differentially Private Empirical Risk Minimization Revisited: Faster and More General
Revisiting Frank-Wolfe: Projection-Free Sparse Convex Optimization
...
1
2
3
4
5
...