paper-with-me

홈 › Papers

Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime

2023-02-27 · Hilal Asi, Vitaly Feldman, Tomer Koren, Kunal Talwar

We consider online learning problems in the realizable setting, where there is a zero-loss solution, and propose new Differentially Private (DP) algorithms that obtain near-optimal regret bounds. For the problem of online prediction from experts, we design new algorithms that obtain near-optimal regret ${O} \big( \varepsilon^{-1} \log^{1.5}{d} \big)$ where $d$ is the number of experts. This significantly improves over the best existing regret bounds for the DP non-realizable setting which are ${O} \big( \varepsilon^{-1} \min\big\{d, T^{1/3}\log d\big\} \big)$. We also develop an adaptive algorithm for the small-loss setting with regret $O(L^\star\log d + \varepsilon^{-1} \log^{1.5}{d})$ where $L^\star$ is the total loss of the best expert. Additionally, we consider DP online convex optimization in the realizable setting and propose an algorithm with near-optimal regret $O \big(\varepsilon^{-1} d^{1.5} \big)$, as well as an algorithm for the smooth case with regret $O \big( \varepsilon^{-2/3} (dT)^{1/3} \big)$, both significantly improving over existing bounds in the non-realizable regime.

📄 PDF Abstract BibTeX arXiv:2302.14154

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Private Online Convex Optimization: Optimal Algorithms in $\ell_p$-Geometry and High Dimensional Contextual Bandits

2022-06-16 · Yuxuan Han, Zhicong Liang, Zhipeng Liang, Yang Wang 외

Differentially private (DP) stochastic convex optimization (SCO) is ubiquitous in trustworthy machine learning algorithm design. This paper studies the DP-SCO problem with streaming data sampled from a distribution and a…

Multi-Armed Bandits

Differentially Private Online-to-Batch for Smooth Losses

2022-10-12 · Qinzi Zhang, Hoang Tran, Ashok Cutkosky

We develop a new reduction that converts any online convex optimization algorithm suffering $O(\sqrt{T})$ regret into an $\epsilon$-differentially private stochastic convex optimization algorithm with the optimal converg…

Private Online Learning via Lazy Algorithms

2024-06-05 · Hilal Asi, Tomer Koren, Daogao Liu, Kunal Talwar

We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We propose a new transformation that transforms lazy online learning algorithms in…

(Nearly) Optimal Algorithms for Private Online Learning in Full-information and Bandit Settings

2013-12-01 · NeurIPS 2013 12 · Abhradeep Guha Thakurta, Adam Smith

We provide a general technique for making online learning algorithms differentially private, in both the full information and bandit settings. Our technique applies to algorithms that aim to minimize a \emph{convex} loss…

Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization

2022-06-01 · Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He

We study differentially private (DP) algorithms for smooth stochastic minimax optimization, with stochastic minimization as a byproduct. The holy grail of these settings is to guarantee the optimal trade-off between the …