D
David H. Wolpert
Researcher at Santa Fe Institute
Publications - 254
Citations - 26998
David H. Wolpert is an academic researcher from Santa Fe Institute. The author has contributed to research in topics: Game theory & Probability distribution. The author has an hindex of 46, co-authored 241 publications receiving 22685 citations. Previous affiliations of David H. Wolpert include Aaron Diamond AIDS Research Center & Los Alamos National Laboratory.
Papers
More filters
Journal ArticleDOI
No free lunch theorems for optimization
TL;DR: A framework is developed to explore the connection between effective optimization algorithms and the problems they are solving and a number of "no free lunch" (NFL) theorems are presented which establish that for any algorithm, any elevated performance over one class of problems is offset by performance over another class.
Journal ArticleDOI
Original Contribution: Stacked generalization
TL;DR: The conclusion is that for almost any real-world generalization problem one should use some version of stacked generalization to minimize the generalization error rate.
Journal ArticleDOI
The lack of a priori distinctions between learning algorithms
TL;DR: It is shown that one cannot say: if empirical misclassification rate is low, the Vapnik-Chervonenkis dimension of your generalizer is small, and the training set is large, then with high probability your OTS error is small.
Posted Content
No Free Lunch Theorems for Search
TL;DR: It is shown that all algorithms that search for an extremum of a cost function perform exactly the same, when averaged over all possible cost functions, which allows for mathematical benchmarks for assessing a particular search algorithm's performance.
Proceedings Article
Bias plus variance decomposition for zero-one loss functions
Ron Kohavi,David H. Wolpert +1 more
TL;DR: It is shown that in practice the naive frequency based estimation of the decompo sition terms is by itself biased and how to correct for this bias is correct.