Minimax Lower Bounds for Cost Sensitive Classification
The cost-sensitive classification problem plays a crucial role in mission-critical machine learning applications, and differs with traditional classification by taking the misclassification costs into consideration. Although being studied extensively in the literature, the fundamental limits of this problem are still not well understood. We investigate the hardness of this problem by extending the standard minimax lower bound of balanced binary classification problem (due to \cite{massart2006risk}), and emphasize the impact of cost terms on the hardness.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningBinary ClassificationClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Minimax Lower Bounds for Realizable Transductive Classification
Transductive learning considers a training set of $m$ labeled samples and a test set of $u$ unlabeled samples, with the goal of best labeling that particular test set. Conversely, inductive learning considers a training …
Binary ClassificationClassificationGeneral ClassificationInductive Learning+1The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy
Privacy-preserving data analysis is a rising challenge in contemporary statistics, as the privacy guarantees of statistical methods are often achieved at the expense of accuracy. In this paper, we investigate the tradeof…
parameter estimationPrivacy PreservingregressionThe Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds
We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent. W…
LEMMAparameter estimationExact Lower Bounds for the Agnostic Probably-Approximately-Correct (PAC) Machine Learning Model
We provide an exact non-asymptotic lower bound on the minimax expected excess risk (EER) in the agnostic probably-ap\-proximately-correct (PAC) machine learning classification model and identify minimax learning algorith…
BIG-bench Machine LearningNonparametric active learning for cost-sensitive classification
Cost-sensitive learning is a common type of machine learning problem where different errors of prediction incur different costs. In this paper, we design a generic nonparametric active learning algorithm for cost-sensiti…
Active LearningClassificationPrediction