Commit caeee290 authored by Petteri Pulkkinen's avatar Petteri Pulkkinen
Browse files

Add refernece


Signed-off-by: Petteri Pulkkinen's avatarPetteri Pulkkinen <petteri.pulkkinen@aalto.fi>
parent 69fa6722
......@@ -2449,6 +2449,7 @@ The appraoch is based on the following:
series = {Proceedings of Machine Learning Research},
volume = {108},
abstract = {Bandit Convex Optimization (BCO) is a fundamental framework for modeling sequential decision-making with partial information, where the only feedback available to the player is the one-point or two-point function values. In this paper, we investigate BCO in non-stationary environments and choose the dynamic regret as the performance measure, which is defined as the difference between the cumulative loss incurred by the algorithm and that of any feasible comparator sequence. Let $T$ be the time horizon and $P_T$ be the path-length of the comparator sequence that reflects the non-stationarity of environments. We propose a novel algorithm that achieves $O(T^{3/4}(1+P_T)^{1/2})$ and $O(T^{1/2}(1+P_T)^{1/2})$ dynamic regret respectively for the one-point and two-point feedback models. The latter result is optimal, matching the $\Omega(T^{1/2}(1+P_T)^{1/2})$ lower bound established in this paper. Notably, our algorithm is more adaptive to non-stationary environments since it does not require prior knowledge of the path-length $P_T$ ahead of time, which is generally unknown.},
comment = {This paper contains notions for universal regret (regret for dynamic environments)},
groups = {Bandit convex optimization},
pdf = {http://proceedings.mlr.press/v108/zhao20b/zhao20b.pdf},
url = {http://proceedings.mlr.press/v108/zhao20b.html},
......@@ -2536,6 +2537,28 @@ The appraoch is based on the following:
groups = {Bandit convex optimization},
}
@Misc{Belmega2018a,
author = {E. Veronica Belmega and Panayotis Mertikopoulos and Romain Negrel and Luca Sanguinetti},
title = {Online convex optimization and no-regret learning: Algorithms, guarantees and applications},
year = {2018},
archiveprefix = {arXiv},
eprint = {1804.04529},
groups = {Bandit convex optimization},
primaryclass = {cs.LG},
}
@Article{McMahan2017,
author = {H. Brendan McMahan},
journal = {Journal of Machine Learning Research},
title = {A survey of algorithms and analysis for adaptive online learning},
year = {2017},
number = {90},
pages = {1--50},
volume = {18},
groups = {Optimization},
url = {http://jmlr.org/papers/v18/14-428.html},
}
@Comment{jabref-meta: databaseType:bibtex;}
@Comment{jabref-meta: grouping:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment