A framework for co-optimization algorithm performance and its application to worst-case optimization

@article{Popovici2015AFF,
  title={A framework for co-optimization algorithm performance and its application to worst-case optimization},
  author={Elena Popovici and Ezra Winston},
  journal={Theor. Comput. Sci.},
  year={2015},
  volume={567},
  pages={46-73}
}
Co-Optimization Free Lunches: Tractability of Optimal Black-Box Algorithms for Maximizing Expected Utility
  • E. Popovici
  • Computer Science
    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.
Bridging Supervised Learning and Test-Based Co-optimization
TLDR
This paper takes a close look at the important commonalities and subtle differences between the well-established field of supervised learning and the much younger one of cooptimization, providing a two-way dictionary for the respective terminologies used to describe these concepts.
Solving complex problems with coevolutionary algorithms
TLDR
His research investigates the utility of coevolutionary methods under non-stationary environments, and uses coev evolution to facilitate the discovery of agents for reinforcement learning tasks in games such as the Arcade Learning Environment, VizDoom and Dota 2.
Solving complex problems with coevolutionary algorithms
Adversarial genetic programming for cyber security: a rising application domain where GP matters
TLDR
A framework called RIVALS is presented which supports the study of network security arms races and its goal is to elucidate the dynamics of cyber networks under attack by computationally modeling and simulating them.
Solving Complex Problems with Coevolutionary Algorithms
TLDR
The work of Krzysztof Krawiec includes problem decomposition using cooperative coevolution, learning strategies for Othello, Go, and other games using competetive CoEAs, and discovery of underlying objectives in test-based problems.

References

SHOWING 1-10 OF 40 REFERENCES
On the practicality of optimal output mechanisms for co-optimization algorithms
TLDR
This paper exhibits the optimal output mechanism for a particular class of co-optimization problems and a certain definition of better overall performance, and provides quantitative characterizations of domains for which this optimal mechanism becomes straightforward to implement.
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
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.
Black-Box Complexity for Bounding the Performance of Randomized Search Heuristics
  • T. Jansen
  • Computer Science
    Theory and Principled Methods for the Design of Metaheuristics
  • 2014
TLDR
This chapter gives a precise and accessible introduction to the notion of black-box complexity, explains important properties and discusses several concrete examples.
Fixed budget computations: a different perspective on run time analysis
TLDR
Two simple randomised search heuristics, random local search and the (1+1) evolutionary algorithm, are analysed on simple and well-known example functions and the potential of this different perspective to provide a more practically useful theory is shown.
A No-Free-Lunch Theorem for Non-Uniform Distributions of Target Functions
The sharpened No-Free-Lunch-theorem (NFL-theorem) states that, regardless of the performance measure, the performance of all optimization algorithms averaged uniformly over any finite set F of
Monotonicity versus performance in co-optimization
TLDR
This analysis points out that even the weakest monotonicity may simply not be within reach for some solution concepts that are nonetheless of practical interest, and hypothesis put forward, in light of recent ``free lunch'' results, is that the authors may be faced with a difficult choice betweenmonotonicity and performance.
...
...