Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective Classification
Year: 2026
Type: preprint
Abstract: Modern machine learning depends heavily on massive datasets, but obtaining high-quality annotations at scale is often expensive. As a result, learning from noisily-labeled data has become common, making accurate estimation of the label-noise transition matrix crucial. However, existing transition matrix estimators rely on the fragile estimation of class-posteriors and do not provide finite-sample performance guarantees. In this work, we propose a novel methodology to estimate the transition matrix based on one-sided selective classification. This approach bypasses class-posterior estimation, provides finite-sample performance guarantees, and leverages flexible learning methods for binary classification. Moreover, we introduce effective algorithms to implement the proposed methodology and provide their refined finite-sample performance bounds.
Source: arXiv (Cornell University)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G121809054, G1280739393, G1480809515, G1577046871, G1633674249, G1717229570, G1747643187, G1855990336, G2309174360, G2660406951, G2785478817, G2992063529, G315595266, G3170287466, G318412399, G3428307696, G3518538256, G3653223248, G4033406476, G430777504, G4554555340, G4993905653, G5195188938, G5403136496, G542055026, G5421974903, G5852410385, G5943232429, G6294024929, G6481147803, G6520718613, G7951220496, G8728224530, G8920660035, G8939903727, G897484643, G99296377
OpenAlex ID: W7215062549