56 search results - page 1 / 12 » (Not) Bounding the True Error |
NIPS
2001
13 years 6 months ago
2001
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
ICML
2005
IEEE
14 years 5 months ago
2005
IEEE
We investigate the empirical applicability of several bounds (a number of which are new) on the true error rate of learned classifiers which hold whenever the examples are chosen ...
ALT
2005
Springer
14 years 1 months ago
2005
Springer
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true ...
TSP
2008
13 years 4 months ago
2008
We develop a nonlinear minimax estimator for the classical linear regression model assuming that the true parameter vector lies in an intersection of ellipsoids. We seek an estimat...
DAGSTUHL
2006
13 years 6 months ago
2006
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true dis...