Robust Estimation Under Heterogeneous Corruption Rates
We study the problem of robust estimation under heterogeneous corruption rates, where each sample may be independently corrupted with a known but non-identical probability. This setting arises naturally in distributed and federated learning, crowdsourcing, and sensor networks, yet existing robust estimators typically assume uniform or worst-case corruption, ignoring structural heterogeneity. For mean estimation for multivariate bounded distributions and univariate gaussian distributions, we give tight minimax rates for all heterogeneous corruption patterns. For multivariate gaussian mean estimation and linear regression, we establish the minimax rate for squared error up to a factor of $\sqrt{d}$, where $d$ is the dimension. Roughly, our findings suggest that samples beyond a certain corruption threshold may be discarded by the optimal estimators -- this threshold is determined by the empirical distribution of the corruption rates given.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Robust Heterogeneous Federated Learning under Data Corruption
Model heterogeneous federated learning is a realistic and challenging problem. However, due to the limitations of data collection, storage, and transmission conditions, as well as the existence of free-rider particip…
Data AugmentationFederated LearningTransfer LearningFraud Type Decomposition and the Observation-Mechanism Taxonomy:Class-Specific Detection Limits in Payment Networks
Fraud detection in payment networks relies on labels generated through heterogeneous and imperfect observation processes, yet existing approaches treat fraud as a homogeneous binary variable. We show that this assumption…
Fraud DetectionOn Robust Mean Estimation under Coordinate-level Corruption
We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measure yields adversary models that capture m…
Matrix CompletionDHAuDS: A Dynamic and Heterogeneous Audio Benchmark for Test-Time Adaptation
Existing Test-time Adaptation (TTA) studies rely heavily on static and homogeneous corruption protocols, such as ImageNet-C and CIFAR-10-C/100-C, leading to inconsistent evaluation settings and potentially inflated robus…
Test-time AdaptationAudio ClassificationOnline and Distributed Robust Regressions under Adversarial Data Corruption
In today's era of big data, robust least-squares regression becomes a more challenging problem when considering the adversarial corruption along with explosive growth of datasets. Traditional robust methods can handle th…
regression