Near-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914815928172544 |
|---|---|
| author | Hu, Bingshan Huang, Zhiming Mehta, Nishant A. Hegde, Nidhi |
| author_facet | Hu, Bingshan Huang, Zhiming Mehta, Nishant A. Hegde, Nidhi |
| contents | In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback. For differentially private stochastic bandits, we propose both UCB and Thompson Sampling-based algorithms that are anytime and achieve the optimal $O \left(\sum_{j: Δ_j>0} \frac{\ln(T)}{\min \left\{Δ_j, ε\right\}} \right)$ instance-dependent regret bound, where $T$ is the finite learning horizon, $Δ_j$ denotes the suboptimality gap between the optimal arm and a suboptimal arm $j$, and $ε$ is the required privacy parameter. For the differentially private full information setting with stochastic rewards, we show an $Ω\left(\frac{\ln(K)}{\min \left\{Δ_{\min}, ε\right\}} \right)$ instance-dependent regret lower bound and an $Ω\left(\sqrt{T\ln(K)} + \frac{\ln(K)}ε\right)$ minimax lower bound, where $K$ is the total number of actions and $Δ_{\min}$ denotes the minimum suboptimality gap among all the suboptimal actions. For the same differentially private full information setting, we also present an $ε$-differentially private algorithm whose instance-dependent regret and worst-case regret match our respective lower bounds up to an extra $\log(T)$ factor. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2102_07929 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Near-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment Hu, Bingshan Huang, Zhiming Mehta, Nishant A. Hegde, Nidhi Machine Learning In this paper, we study differentially private online learning problems in a stochastic environment under both bandit and full information feedback. For differentially private stochastic bandits, we propose both UCB and Thompson Sampling-based algorithms that are anytime and achieve the optimal $O \left(\sum_{j: Δ_j>0} \frac{\ln(T)}{\min \left\{Δ_j, ε\right\}} \right)$ instance-dependent regret bound, where $T$ is the finite learning horizon, $Δ_j$ denotes the suboptimality gap between the optimal arm and a suboptimal arm $j$, and $ε$ is the required privacy parameter. For the differentially private full information setting with stochastic rewards, we show an $Ω\left(\frac{\ln(K)}{\min \left\{Δ_{\min}, ε\right\}} \right)$ instance-dependent regret lower bound and an $Ω\left(\sqrt{T\ln(K)} + \frac{\ln(K)}ε\right)$ minimax lower bound, where $K$ is the total number of actions and $Δ_{\min}$ denotes the minimum suboptimality gap among all the suboptimal actions. For the same differentially private full information setting, we also present an $ε$-differentially private algorithm whose instance-dependent regret and worst-case regret match our respective lower bounds up to an extra $\log(T)$ factor. |
| title | Near-Optimal Algorithms for Differentially Private Online Learning in a Stochastic Environment |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2102.07929 |