arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.14095cs.CCcs.CRcs.LGcs.LO
收藏

电路下界的学习算法

Learning algorithms from circuit lower bounds

University of Oxford(牛津大学)

Ján Pich

摘要:

我们重新审视已知的有效的学习算法的建设性电路下界,如破坏伪随机发生器或有效的见证算法,发现错误的小电路试图计算硬函数的各种概念。作为我们的主要结果,我们证明,如果它是可能的,以一种特定的互动方式,许多p-大小的电路试图解决困难的问题,错误的有效地找到,那么p-大小的电路可以PAC学习均匀分布的成员查询的次指数大小的电路。相反的含义也成立。这为学习算法提供了一个新的刻画,并扩展了Razborov和Rudich的自然证明屏障。该证明基于Krajíček(2010)提出的利用Nisan-Wigderson生成器的方法,并用于分析有界算术中电路下界的复杂性。从电路下界构造学习算法的一个有趣结果是Oliveira和Santhanam(2016)的学习加速。我们提出了这种现象的另一种证明,并讨论了它推进硬度放大计划的潜力。

英文摘要:

We revisit known constructions of efficient learning algorithms from various notions of constructive circuit lower bounds such as distinguishers breaking pseudorandom generators or efficient witnessing algorithms which find errors of small circuits attempting to compute hard functions. As our main result we prove that if it is possible to find efficiently, in a particular interactive way, errors of many p-size circuits attempting to solve hard problems, then p-size circuits can be PAC learned over the uniform distribution with membership queries by circuits of subexponential size. The opposite implication holds as well. This provides a new characterisation of learning algorithms and extends the natural proofs barrier of Razborov and Rudich. The proof is based on a method of exploiting Nisan-Wigderson generators introduced by Krajíček (2010) and used to analyze complexity of circuit lower bounds in bounded arithmetic. An interesting consequence of known constructions of learning algorithms from circuit lower bounds is a learning speedup of Oliveira and Santhanam (2016). We present an alternative proof of this phenomenon and discuss its potential to advance the program of hardness magnification.

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。

↑