arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2511.08073cs.LGstat.ML
收藏

带付费随机特征的在线线性回归

Online Linear Regression with Paid Stochastic Features

Nadav Merlis, Kyoungseok Jang, Nicolò Cesa-Bianchi

AI总结:

针对观测特征含噪声且可付费降噪声的在线线性回归场景,结合预测误差与付费定义损失,推导得付费-噪声映射已知时遗憾率最优为√T、未知时为T²/³阶,分析利用矩阵鞅集中性验证经验损失收敛性。

摘要:

我们研究了一种在线线性回归场景:观测到的特征向量受噪声干扰,学习者可通过付费降低噪声水平。实践中这种情况存在多种原因,例如使用更昂贵设备能更准确地测量特征,或激励数据提供者发布隐私性较低的特征。假设特征向量独立同分布地来自固定但未知的分布,我们衡量学习者相对于线性预测器的遗憾,该预测器最小化结合预测误差与付费的损失。当付费与噪声协方差的映射已知时,若忽略对数因子,我们证明遗憾率√T是最优的;当噪声协方差未知时,最优遗憾率为T²/³阶(忽略对数因子)。我们的分析利用矩阵鞅集中性,证明经验损失对所有付费和线性预测器均一致收敛于期望损失。

英文摘要:

We study an online linear regression setting in which the observed feature vectors are corrupted by noise and the learner can pay to reduce the noise level. In practice, this may happen for several reasons: for example, because features can be measured more accurately using more expensive equipment, or because data providers can be incentivized to release less private features. Assuming feature vectors are drawn i.i.d. from a fixed but unknown distribution, we measure the learner's regret against the linear predictor minimizing a notion of loss that combines the prediction error and payment. When the mapping between payments and noise covariance is known, we prove that the rate $\sqrt{T}$ is optimal for regret if logarithmic factors are ignored. When the noise covariance is unknown, we show that the optimal regret rate becomes of order $T^{2/3}$ (ignoring log factors). Our analysis leverages matrix martingale concentration, showing that the empirical loss uniformly converges to the expected one for all payments and linear predictors.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑