Papers on Estimation of Distribution Algorithms

Estimation of distribution algorithms (EDAs) use machine learning techniques to solve optimization problems, by trying to learn the locations of the more promising regions of the search space. In particular, a probabilistic model, such as a graphical model, is used to generate candidate solutions, and learning is used to adapt the probability model to explore more promising regions of space.

Most of the research in this field has been focused on producing new algorithms based around new probability models or learning rules. My research is focused on understanding how they work, why they can fail, and based on the previous two points, how they can be improved.

1

Hao Wu and Jonathan L. Shapiro.
Does overfitting affect performance in estimation of distribution algorithms.
In Proceedings of Genetic and Evolutionary Computation Conference (GECCO) 2006, Seattle, 2006.

2

Jonathan L. Shapiro.
Diversity loss in general estimation of distibution algorithms.
Lecture Notes in Computer Science, 4193:92-101, 2006.
(abstract, full paper)

3

Elon S. Correa and Jonathan L. Shapiro.
Model complexity vs. performance in the Bayesian optimization algorithm.
Lecture Notes in Computer Science, 4193:998-1007, 2006.
(Abstract available from SpringerLink web site. Full text available to SpringerLink subscribers)

4

J. L. Shapiro.
Drift and scaling in estimation of distribution algorithms.
Evolutionary Computation, 13(1):99-125, 2005.
(Abstract available from Evolutionary Computation (MIT Press) web site.)

5

E. S. Correa and J. L. Shapiro.
A study of the effect of detailed balance on PBIL in $k$-sat and the $p$-median problem.
In International Conference on Advances in Soft Computing, 2002.

6

J. L. Shapiro.
Scaling of probability-based optimization algorithms.
Advances in Neural Information Processing, 15, 2003.
(abstract, full paper)

7

J. L. Shapiro.
The sensitivity of PBIL to its learning rate, and how detailed balance can remove it.
In Carlos Cotta, Kenneth de Jong, Riccardo Poli, and Jonathan Rowe, editors, Foundations of Genetic Algorithms VII. Morgan Kaufmann, 2002.
(abstract, full paper)

8

A. Johnson and J. L. Shapiro.
The importance of selection mechanisms in distribution estimation algorithms.
In Proceedings of the $5^{\mbox{th}}$ International Conference on Artificial Evolution AE01, 2001.
(abstract, full paper)