多个随机神谕比一个更好
Multiple Random Oracles Are Better Than One
摘要:
我们研究的问题,学习k-juntas给定访问的例子从一些不同的产品分布。因此,我们希望学习一个依赖于k(未知)坐标的函数f:{-1,1}^n -> {-1,1}。虽然学习k-junta的一般问题的最著名的算法需要运行时间n^k * poly(n,2^k),但我们表明,如果访问k个不同的乘积分布,偏差由γ>0分隔,则可以在时间poly(n,2^k,γ^{-k})中学习函数。更一般地,给定对t <= k个不同乘积分布的访问,可以在时间上学习函数n^{k/t} * poly(n,2 ^k,γ^{-k})。我们的技术涉及傅立叶分析中的新结果,涉及傅立叶展开相对于不同的偏见和Russo公式的推广。
英文摘要:
We study the problem of learning k-juntas given access to examples drawn from a number of different product distributions. Thus we wish to learn a function f : {-1,1}^n -> {-1,1} that depends on k (unknown) coordinates. While the best known algorithms for the general problem of learning a k-junta require running time of n^k * poly(n,2^k), we show that given access to k different product distributions with biases separated by γ>0, the functions may be learned in time poly(n,2^k,γ^{-k}). More generally, given access to t <= k different product distributions, the functions may be learned in time n^{k/t} * poly(n,2^k,γ^{-k}). Our techniques involve novel results in Fourier analysis relating Fourier expansions with respect to different biases and a generalization of Russo's formula.
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。