WORST-CASE QUADRATIC LOSS BOUNDS FOR ON-LINE PREDICTION OF LINEAR FUNCTIONS BY GRADIENT DESCENT
暂无分享,去创建一个
[1] Richard O. Duda,et al. Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.
[2] Charles R. Johnson,et al. Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.
[3] Michael I. Jordan,et al. Advances in Neural Information Processing Systems 30 , 1995 .
[4] Vladimir Vovk,et al. Aggregating strategies , 1990, COLT '90.
[5] M. Zwaan. An introduction to hilbert space , 1990 .
[6] Philip M. Long,et al. On-line learning of linear functions , 1991, STOC '91.
[7] Neri Merhav,et al. Universal sequential learning and decision from individual data sequences , 1992, COLT '92.
[8] Philip M. Long,et al. The learning complexity of smooth functions of a single variable , 1992, COLT '92.
[9] Neri Merhav,et al. Universal prediction of individual sequences , 1992, IEEE Trans. Inf. Theory.
[10] David Haussler,et al. How to use expert advice , 1993, STOC.
[11] Manfred K. Warmuth,et al. The Weighted Majority Algorithm , 1994, Inf. Comput..