arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1608.04544math.OCcs.AI
收藏

泛分布下优化的免费午餐

Free Lunch for Optimisation under the Universal Distribution

Stockholm University(斯德哥尔摩大学);University of Alberta(阿尔伯塔大学);Australian National University(澳大利亚国立大学)

Tom Everitt, Tor Lattimore, Marcus Hutter

摘要:

函数优化是计算机科学中的一个主要挑战。没有免费的午餐定理指出,如果假设所有具有相同直方图的函数都是同样可能的,那么没有算法在预期中优于任何其他算法。我们反对统一的假设,并建议普遍存在的事先有一个免费的午餐,但没有特定的类的功能是优于另一个。我们还证明了上界和下界的大小的免费午餐。

英文摘要:

Function optimisation is a major challenge in computer science. The No Free Lunch theorems state that if all functions with the same histogram are assumed to be equally probable then no algorithm outperforms any other in expectation. We argue against the uniform assumption and suggest a universal prior exists for which there is a free lunch, but where no particular class of functions is favoured over another. We also prove upper and lower bounds on the size of the free lunch.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑