Toward Efficient Agnostic Learning
Toward Efficient Agnostic Learning
M. Kearns,R. Schapire,Linda Sellie
1992 · DOI: 10.1023/A:1022615600103
Annual Conference Computational Learning Theory · 146 Citations
TLDR
An investigation of generalizations of the Probably Approximately Correct (PAC) learning model that attempt to significantly weaken the target function assumptions is initiated, providing an initial outline of the possibilities for agnostic learning.