Learning from binary labels with instance-dependent noise
From MaRDI portal
Publication:1631810
DOI10.1007/s10994-018-5715-3zbMath1475.68286OpenAlexW2804975550MaRDI QIDQ1631810
Nagarajan Natarajan, Aditya Krishna Menon, Brendan van Rooyen
Publication date: 7 December 2018
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10994-018-5715-3
Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)
Related Items (4)
Binary classification with corrupted labels ⋮ Beyond confusion matrix: learning from multiple annotators with awareness of instance features ⋮ Unnamed Item ⋮ Adaptive transfer learning
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- AlexNet
- Classification with asymmetric label noise: consistency and maximal denoising
- Risk bounds for statistical learning
- A polynomial-time algorithm for learning noisy linear threshold functions
- Learning kernel logistic regression in the presence of class label noise
- Statistical behavior and consistency of classification methods based on convex risk minimization.
- Ranking and empirical minimization of \(U\)-statistics
- Exact Recoverability From Dense Corrupted Observations via $\ell _{1}$-Minimization
- The Power of Localization for Efficiently Learning Linear Separators with Noise
- An Empirical Distribution Function for Sampling with Incomplete Information
- Learning Kernel Perceptrons on Noisy Data Using Random Projections
- Agnostically Learning Halfspaces
- Dense Error Correction Via $\ell^1$-Minimization
- Learning Theory
- Learning Theory
- Convexity, Classification, and Risk Bounds
This page was built for publication: Learning from binary labels with instance-dependent noise