Mitigating Bias in Adaptive Data Gathering via Differential Privacy
Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased downwards --- and when gathering more complicated data --- running hypothesis tests on complex data gathered via contextual bandit algorithms leads to false discovery. In this paper, we show that this problem is mitigated if the data collection procedure is differentially private. This lets us both bound the bias of simple numeric valued quantities (like the empirical means of stochastic bandit algorithms), and correct the p-values of hypothesis tests run on the adaptively gathered data. Moreover, there exist differentially private bandit algorithms with near optimal regret bounds: we apply existing theorems in the simple stochastic case, and give a new analysis for linear contextual bandits. We complement our theoretical results with experiments validating our theory.
Code (0)
등록된 구현이 없습니다.
Tasks
Multi-Armed BanditsSimilar Papers 제목 키워드 기반
Gender Bias in Machine Translation
Machine translation (MT) technology has facilitated our daily tasks by providing accessible shortcuts for gathering, elaborating and communicating information. However, it can suffer from biases that harm users and socie…
Machine TranslationTranslationAn Adaptive Differentially Private Federated Learning Framework
Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (N…
Dimensionality ReductionFederated LearningFair Differential Privacy Can Mitigate the Disparate Impact on Model Accuracy
The techniques based on the theory of differential privacy (DP) has become a standard building block in the machine learning community. DP training mechanisms offer strong guarantees that an adversary cannot determine wi…
FairnessMitigating spectral bias for the multiscale operator learning
Neural operators have emerged as a powerful tool for learning the mapping between infinite-dimensional parameter and solution spaces of partial differential equations (PDEs). In this work, we focus on multiscale PDEs tha…
Operator learningMitigating Statistical Bias within Differentially Private Synthetic Data
Increasing interest in privacy-preserving machine learning has led to new and evolved approaches for generating private synthetic data from undisclosed real data. However, mechanisms of privacy preservation can significa…
Privacy Preserving