• Publications
  • Influence
Stacked generalization
  • D. Wolpert
  • Mathematics, Computer Science
  • Neural Networks
  • 5 February 1992
TLDR
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. Expand
No free lunch theorems for optimization
A framework is developed to explore the connection between effective optimization algorithms and the problems they are solving. A number of "no free lunch" (NFL) theorems are presented whichExpand
No Free Lunch Theorems for Search
We show that all algorithms that search for an extremum of a cost function perform exactly the same, when averaged over all possible cost functions. In particular, if algorithm A outperformsExpand
Bias Plus Variance Decomposition for Zero-One Loss Functions
TLDR
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. Expand
An Introduction to Collective Intelligence
This paper surveys the emerging science of how to design a “COllective INtelligence” (COIN). A COIN is a large multi-agent system where: i) There is little to no centralized communication or control.Expand
The Lack of A Priori Distinctions Between Learning Algorithms
  • D. Wolpert
  • Computer Science, Mathematics
  • Neural Computation
  • 1 October 1996
TLDR
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. Expand
Collective Intelligence
  • D. Wolpert
  • Computer Science
  • Encyclopedia of Social Network Analysis and…
  • 2014
TLDR
This paper presents an introduction to the science of such systems of self-interested agents, which are often very large, distributed, and support little if any centralized communication and control, although those characteristics are not part of their formal definition. Expand
The Supervised Learning No-Free-Lunch Theorems
This paper reviews the supervised learning versions of the no-free-lunch theorems in a simplified form. It also discusses the significance of those theorems, and their relation to other aspects ofExpand
Optimal Payoff Functions for Members of Collectives
TLDR
It is demonstrated experimentally that using these new utility functions can result in significantly improved performance over that of previously investigated COIN payoff utilities, over and above those previous utilities' superiority to the conventional team game utility. Expand
Information Theory - The Bridge Connecting Bounded Rational Game Theory and Statistical Physics
  • D. Wolpert
  • Mathematics, Computer Science
  • ArXiv
  • 19 February 2004
TLDR
This paper shows that the same information theoretic mathematical structure, known as Product Distribution (PD) theory, addresses both bounded rationality and mean field theory in statistical physics, and shows that those topics are fundamentally one and the same. Expand
...
1
2
3
4
5
...