The unrestricted black-box complexity of jump functions
Pages 1 - 2
Abstract
We analyze the unrestricted black-box complexity of the n-dimensional Jump function classes. We show very precise bounds for various values of the jump size ℓ, including a novel [EQUATION] bound for the extreme case that only the middle one (for n even) or the middle two (for n odd) Hamming levels are not part of the plateau surrounding the optimum. To obtain these results, we significantly extend the classic information theoretic argument. It now allows to exploit structural properties of the underlying optimization problems, whereas before it relied only on the number of different fitness values.
This abstract for the GECCO'17 Hot-off-the-Press track summarizes work that appeared as M. Buzdalov, B. Doerr, and M. Kever. The unrestricted black-box complexity of jump functions. Evolutionary Computation, 24(4):719--744, 2016 [4].
References
[1]
P. Afshani, M. Agrawal, B. Doerr, C. Doerr, K. G. Larsen, and K. Mehlhorn. The query complexity of finding a hidden permutation. In Space-Efficient Data Structures, Streams, and Algorithms, number 8066 in Lecture Notes in Computer Science, pages 1--11. Springer, 2013.
[2]
G. Anil and R. P. Wiegand. Black-box search by elimination of fitness functions. In Proceedings of Foundations of Genetic Algorithms, pages 67--78, 2009.
[3]
G. Badkobeh, P. K. Lehre, and D. Sudholt. Unbiased black-box complexity of parallel search. In Parallel Problem Solving from Nature XIII, number 8672 in Lecture Notes in Computer Science, pages 892--901. Springer, 2014.
[4]
M. Buzdalov, B. Doerr, and M. Kever. The unrestricted black-box complexity of jump functions. Evolutionary Computation, 24(4):719--744, 2016.
[5]
B. Doerr, C. Doerr, and F. Ebel. From black-box complexity to designing new genetic algorithms. Theoretical Computer Science, 567:87--104, 2015.
[6]
B. Doerr, C. Doerr, and T. Kötzing. The unbiased black-box complexity of partition is polynomial. Artificial Intelligence, 216:275--286, 2014.
[7]
B. Doerr, C. Doerr, and T. Kötzing. Unbiased black-box complexities of jump functions. Evolutionary Computation, 2017. To appear. Preliminary version in GECCO 2014.
[8]
B. Doerr, T. Kötzing, J. Lengler, and C. Winzen. Black-box complexities of combinatorial problems. Theoretical Computer Science, 471:84--106, 2013.
[9]
B. Doerr, H. P. Le, R. Makhmara, and T. D. Nguyen. Fast genetic algorithms. In Proceedings of Genetic and Evolutionary Computation Conference. ACM, 2017.
[10]
B. Doerr and C. Winzen. Playing Mastermind with constant-size memory. Theory of Computing Systems, 55(4):658--684, 2014.
[11]
B. Doerr and C. Winzen. Ranking-based black-box complexity. Algorithmica, 68(3):571--609, 2014.
[12]
C. Doerr and J. Lengler. Elitist black-box models: Analyzing the impact of elitist selection on the performance of evolutionary algorithms. In Proceedings of Genetic and Evolutionary Computation Conference, pages 839--846. ACM, 2015.
[13]
S. Droste, T. Jansen, K. Tinnefeld, and I. Wegener. A new framework for the valuation of algorithms for black-box optimization. In Proceedings of Foundations of Genetic Algorithms, pages 253--270. Morgan Kaufmann, 2003.
[14]
S. Droste, T. Jansen, and I. Wegener. Upper and lower bounds for randomized search heuristics in black-box optimization. Theory of Computing Systems, 39(4):525--544, 2006.
[15]
T. Jansen. On the black-box complexity of example functions: The real Jump function. In Proceedings of Foundations of Genetic Algorithms, pages 16--24. ACM, 2015.
[16]
P. K. Lehre and C. Witt. Black-box search by unbiased variation. In Proceedings of Genetic and Evolutionary Computation Conference, pages 1441--1448. ACM, 2010.
[17]
P. K. Lehre and C. Witt. Black-box search by unbiased variation. Algorithmica, 64:623--642, 2012.
[18]
J. Rowe and M. Vose. Unbiased black box search algorithms. In Proceedings of Genetic and Evolutionary Computation Conference, pages 2035--2042. ACM, 2011.
Recommendations
The unrestricted black-box complexity of jump functions
We analyze the unrestricted black-box complexity of the Jump function classes for different jump sizes. For upper bounds, we present three algorithms for small, medium, and extreme jump sizes. We prove a matrix lower bound theorem which is capable of ...
Unbiased black-box complexities of jump functions: how to cross large plateaus
GECCO '14: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary ComputationWe analyze the unbiased black-box complexity of jump functions with large jump sizes. Among other results, we show that when the jump size is (1/2 - epsilon)n, that is, only a small constant fraction of the fitness values is visible, then the unbiased ...
Unbiased black-box complexities of jump functions
We analyze the unbiased black-box complexities of jump functions with small, medium, and large sizes of the fitness plateau surrounding the optimal solution. Among other results, we show that when the jump size is <inline-formula><inline-graphic xlink="...
Comments
Information & Contributors
Information
Published In
July 2017
1934 pages
ISBN:9781450349390
DOI:10.1145/3067695
Copyright © 2017 Owner/Author.
Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 15 July 2017
Check for updates
Qualifiers
- Abstract
Funding Sources
Conference
GECCO '17
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,669 of 4,410 submissions, 38%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 77Total Downloads
- Downloads (Last 12 months)3
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in