paper-with-me

홈 › Papers

Minimax Lower Bounds for Cost Sensitive Classification

2018-05-20 · Parameswaran Kamalaruban, Robert C. Williamson

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.

📄 PDF Abstract BibTeX arXiv:1805.07723

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningBinary ClassificationClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Minimax Lower Bounds for Realizable Transductive Classification

2016-02-09 · Ilya Tolstikhin, David Lopez-Paz

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+1

The Cost of Privacy: Optimal Rates of Convergence for Parameter Estimation with Differential Privacy

2019-02-12 · T. Tony Cai, Yichen Wang, Linjun Zhang

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 Preservingregression

The Cost of Privacy in Generalized Linear Models: Algorithms and Minimax Lower Bounds

2020-11-08 · T. Tony Cai, Yichen Wang, Linjun Zhang

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 estimation

Exact Lower Bounds for the Agnostic Probably-Approximately-Correct (PAC) Machine Learning Model

2016-06-29 · Aryeh Kontorovich, Iosif Pinelis

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 Learning

Nonparametric active learning for cost-sensitive classification

2023-09-30 · Boris Ndjia Njike, Xavier Siebert

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