Safe Linear Bandits over Unknown Polytopes
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909235696107520 |
|---|---|
| author | Gangrade, Aditya Chen, Tianrui Saligrama, Venkatesh |
| author_facet | Gangrade, Aditya Chen, Tianrui Saligrama, Venkatesh |
| contents | The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints, under stochastic bandit feedback of rewards and safety risks of actions. We study the tradeoffs between efficacy and smooth safety costs of SLBs over polytopes, and the role of aggressive doubly-optimistic play in avoiding the strong assumptions made by extant pessimistic-optimistic approaches.
We first elucidate an inherent hardness in SLBs due the lack of knowledge of constraints: there exist `easy' instances, for which suboptimal extreme points have large `gaps', but on which SLB methods must still incur $Ω(\sqrt{T})$ regret or safety violations, due to an inability to resolve unknown optima to arbitrary precision. We then analyse a natural doubly-optimistic strategy for the safe linear bandit problem, DOSS, which uses optimistic estimates of both reward and safety risks to select actions, and show that despite the lack of knowledge of constraints or feasible points, DOSS simultaneously obtains tight instance-dependent $O(\log^2 T)$ bounds on efficacy regret, and $\tilde O(\sqrt{T})$ bounds on safety violations. Further, when safety is demanded to a finite precision, violations improve to $O(\log^2 T).$ These results rely on a novel dual analysis of linear bandits: we argue that \algoname proceeds by activating noisy versions of at least $d$ constraints in each round, which allows us to separately analyse rounds where a `poor' set of constraints is activated, and rounds where `good' sets of constraints are activated. The costs in the former are controlled to $O(\log^2 T)$ by developing new dual notions of gaps, based on global sensitivity analyses of linear programs, that quantify the suboptimality of each such set of constraints. The latter costs are controlled to $O(1)$ by explicitly analysing the solutions of optimistic play. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_13694 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Safe Linear Bandits over Unknown Polytopes Gangrade, Aditya Chen, Tianrui Saligrama, Venkatesh Machine Learning The safe linear bandit problem (SLB) is an online approach to linear programming with unknown objective and unknown roundwise constraints, under stochastic bandit feedback of rewards and safety risks of actions. We study the tradeoffs between efficacy and smooth safety costs of SLBs over polytopes, and the role of aggressive doubly-optimistic play in avoiding the strong assumptions made by extant pessimistic-optimistic approaches. We first elucidate an inherent hardness in SLBs due the lack of knowledge of constraints: there exist `easy' instances, for which suboptimal extreme points have large `gaps', but on which SLB methods must still incur $Ω(\sqrt{T})$ regret or safety violations, due to an inability to resolve unknown optima to arbitrary precision. We then analyse a natural doubly-optimistic strategy for the safe linear bandit problem, DOSS, which uses optimistic estimates of both reward and safety risks to select actions, and show that despite the lack of knowledge of constraints or feasible points, DOSS simultaneously obtains tight instance-dependent $O(\log^2 T)$ bounds on efficacy regret, and $\tilde O(\sqrt{T})$ bounds on safety violations. Further, when safety is demanded to a finite precision, violations improve to $O(\log^2 T).$ These results rely on a novel dual analysis of linear bandits: we argue that \algoname proceeds by activating noisy versions of at least $d$ constraints in each round, which allows us to separately analyse rounds where a `poor' set of constraints is activated, and rounds where `good' sets of constraints are activated. The costs in the former are controlled to $O(\log^2 T)$ by developing new dual notions of gaps, based on global sensitivity analyses of linear programs, that quantify the suboptimality of each such set of constraints. The latter costs are controlled to $O(1)$ by explicitly analysing the solutions of optimistic play. |
| title | Safe Linear Bandits over Unknown Polytopes |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2209.13694 |