论文信息 - An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution - 字舞流文

An upper bound on the sample complexity of PAC-learning halfspaces with respect to the uniform distribution

We show that halfspaces in n dimensions can be PAC-learned with respect to the uniform distribution with accuracy e and confidence δ using O(1/e- (n + log 1/δ)) examples.

[1] Béla Bollobás,et al. Random Graphs , 1985 .

[2] D. Pollard. Convergence of stochastic processes , 1984 .

[3] David Haussler,et al. Predicting {0,1}-functions on randomly drawn points , 1988, COLT '88.

[4] Aravind Srinivasan,et al. Approximating Hyper-Rectangles: Learning and Pseudorandom Sets , 1998, J. Comput. Syst. Sci..

[5] H. Robbins. A Remark on Stirling’s Formula , 1955 .

[6] Philip M. Long. On the sample complexity of PAC learning half-spaces against the uniform distribution , 1995, IEEE Trans. Neural Networks.

[7] Aravind Srinivasan,et al. Approximating hyper-rectangles: learning and pseudo-random sets , 1997, STOC '97.

[8] Thomas M. Cover,et al. Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[9] Nick Littlestone,et al. From on-line to batch learning , 1989, COLT '89.

[10] H. Balsters,et al. Learnability with respect to fixed distributions , 1991 .

[11] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.

[12] Rocco A. Servedio,et al. On PAC learning using Winnow, Perceptron, and a Perceptron-like algorithm , 1999, COLT '99.

[13] David Haussler,et al. Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.