TY - JOUR
T1 - On universal learning algorithms
AU - Goldreich, Oded
AU - Ron, Dana
N1 - Funding Information:
* Corresponding author. Email: oded@wisdom.weizmann.ac.il. On sabbatical leave at LCS, MIT. ’ Presented in the Impromptu Session of COL796. * Email: danar@theory.lcs.mit.edu. Research was supported in part by an NSF Postdoctoral Fellowship.
PY - 1997/8/14
Y1 - 1997/8/14
N2 - We observe that there exists a universal learning algorithm that PAC-learns every concept class within complexity that is linearly related to the complexity of the best learning algorithm for this class. This observation is derived by an adaptation, to the learning context, of Levin's proof of the existence of optimal algorithms for NP.
AB - We observe that there exists a universal learning algorithm that PAC-learns every concept class within complexity that is linearly related to the complexity of the best learning algorithm for this class. This observation is derived by an adaptation, to the learning context, of Levin's proof of the existence of optimal algorithms for NP.
KW - PAC-learning
KW - Theorey of computation
UR - http://www.scopus.com/inward/record.url?scp=0031210449&partnerID=8YFLogxK
U2 - 10.1016/s0020-0190(97)00117-8
DO - 10.1016/s0020-0190(97)00117-8
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:0031210449
VL - 63
SP - 131
EP - 136
JO - Information Processing Letters
JF - Information Processing Letters
SN - 0020-0190
IS - 3
ER -