摘要：There has been a line of work trying to characterize BPP (the class of languages that are solvable by efficient randomized algorithms) by efficient nonadaptive reductions to the set of Kolmogorov-random strings: Buhrman, Fortnow, Koucký, and Loff (CCC 2010 [Buhrman et al., 2010]) showed that every language in BPP is reducible to the set of random strings via a polynomial-time nonadaptive reduction (irrespective of the choice of a universal Turing machine used to define Kolmogorov-random strings). It was conjectured by Allender (CiE 2012 [Allender, 2012]) and others that their lower bound is tight when a reduction works for every universal Turing machine; i.e., "the only way to make use of random strings by a nonadaptive polynomial-time algorithm is to derandomize BPP." In this paper, we refute this conjecture under the plausible assumption that the exponential-time hierarchy does not collapse, by showing that the exponential-time hierarchy EXPH can be solved in exponential time by nonadaptively asking the oracle whether a string is Kolmogorov-random or not. In addition, we provide an exact characterization of S_2^{exp} in terms of exponential-time-computable nonadaptive reductions to arbitrary dense subsets of random strings.
