The Perspectron algorithm matches the random-noise sample complexity for PAC learning halfspaces with Massart noise, and extends to generalized linear models.
Coloring random and semi-random k-colorable graphs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
The Perspectron algorithm matches the random-noise sample complexity for PAC learning halfspaces with Massart noise, and extends to generalized linear models.