• Corpus ID: 126279242

A Fitness Function Elimination Theory For Blackbox Optimization And Problem Class Learning

@inproceedings{Anil2012AFF,
  title={A Fitness Function Elimination Theory For Blackbox Optimization And Problem Class Learning},
  author={Gautham Anil},
  year={2012}
}
The modern view of optimization is that optimization algorithms are not designed in a vacuum, but can make use of information regarding the broad class of objective functions from which a problem instance is drawn. Using this knowledge, we want to design optimization algorithms that execute quickly (efficiency), solve the objective function with minimal samples (performance), and are applicable over a wide range of problems (abstraction). However, we present a new theory for blackbox… 

Figures from this paper

Co-Optimization Free Lunches: Tractability of Optimal Black-Box Algorithms for Maximizing Expected Utility
  • E. Popovici
  • Computer Science, Medicine
    Evolutionary Computation
  • 2018
TLDR
The design of generally well-performing black-box algorithms for expected-utility maximization problems is interested, that is, algorithms which have access to the utility function only via input–output queries.

References

SHOWING 1-10 OF 63 REFERENCES
Black-box search by elimination of fitness functions
TLDR
Though in its early stages, it is believed that there is utility in search methods based on ideas from the elimination of functions method, and that the viewpoint provides promise and new insight about black-box optimization.
A New Framework for the Valuation of Algorithms for Black-Box Optimization
TLDR
It can be concluded that randomized search heuristics whose (worst-case) expected optimization time for some problem is close to the black-box complexity of the problem are provably efficient (in theblack-box scenario).
Comparison of public-domain software for black box global optimization
We instance our experience with six public-domain global optimization software products and report comparative computational results obtained on a set of eleven test problems. The techniques used by
Toward the optimization of a class of black box optimization algorithms
  • G. Wang, E. Goodman, W. Punch
  • Computer Science
    Proceedings Ninth IEEE International Conference on Tools with Artificial Intelligence
  • 1997
TLDR
This work discusses the process of algorithm design and operation, and proposes an approach toward the optimization of a process for controlling a specific class of systems, and its application to dynamic adjustment of the algorithm used in the search problem.
Automatic heuristic generation with genetic programming: evolving a jack-of-all-trades or a master of one
TLDR
A Genetic Programming system can automate the process of heuristic generation and produce heuristics that are human-competitive over a range of sets of problems, or which excel on a particular sub-set.
Reducing Local Optima in Single-Objective Problems by Multi-objectivization
TLDR
This paper uses an abstract building-block problem to illustrate how 'multi-objectivizing' a single-objective optimization (SOO) problem can remove local optima, and investigates small instances of the travelling salesman problem where additional objectives are defined using arbitrary sub-tours.
SEARCH, Blackbox Optimization, And Sample Complexity
TLDR
A closed form bound on the sample complexity in terms of the cardinality of the relation space, class space, desired quality of the solution and the reliability is presented and leads to the identification of the class of order-k delineable problems that can be solved in polynomial sample complexity.
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 which
Perhaps Not a Free Lunch But At Least a Free Appetizer
TLDR
It is argued why the scenario on which the No Free Lunch Theorem is based does not model real life optimization, and why optimization techniques differ in their efficiency.
Black-box complexities of combinatorial problems
TLDR
This work reveals that the choice of how to model the optimization problem is non-trivial here and comes true where the search space does not consist of bit strings and where a reasonable definition of unbiasedness has to be agreed on.
...
1
2
3
4
5
...