Scott Decatur, Efficient Learning from Faulty Data. Ph.D. Thesis, Harvard University, TR-30-95, 1995. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
On Learning Correlated Boolean Functions Using Statistical Query - Yang (Correct)
....mostly used definition of a normal SQ oracle (sometimes denoted as STATf ) as in [AD98, BFJ 94, BFK 96, BKW00, K98] Actually an honest SQ oracle is stronger than a normal SQ oracle. Kearns [K98] proved that one can simulate a STATf oracle efficiently in the PAC learning framework, and Decatur [D95] extensively studied the problem of efficiently simulating a STATf oracle. Both their results can be easily extended to show that an honest SQ oracle can be used to efficiently simulate a normal SQ oracle. Therefore a lower bound with respect to an honest SQ oracle automatically translates to a ....
Scott Decatur, Efficient Learning from Faulty Data. Ph.D. Thesis, Harvard University, TR-30-95, 1995.
Learning in Hybrid Noise Environments Using Statistical Queries - Decatur (1995) (3 citations) Self-citation (Decatur) (Correct)
....ffi ) Learning in Hybrid Noise Environments Using Statistical Queries 267 if Q is infinite with finite VC dimension q. Alternatively, one could use a separate sample for each of the N queries made by all runs of the algorithm, thus using a total of m = O( N 2 log N ffi ) examples. See [Dec95] for a more complete discussion of sample sizes. 2 25.3.4 Optimality of CAM Tolerance Theorem 3 states that any class which is SQ learnable is PAC learnable with CAM for all j 1 2 and fi = O( 1=2 Gamma j) Omega Gamma 1 1=2 Gammaj ) Aslam and Decatur [AD93] have shown that for any ....
Scott Decatur. Efficient Learning from Faulty Data. PhD thesis, Harvard University, 1995.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC