Answers are grounded in this paper and cite their sources.
It is shown that a random restriction leaving only a fraction ϵ of the input variables unassigned reduces the expected de Morgan formula size of the induced function by a factor ofO(E(5−√2)/2) =O(ϵ1.63). (A de Morgan, or unate, formula is a formula over the basis {∧, ∨, ¬}.) This improves a long‐standing result ofO(ϵ1.5) by Subbotovskaya and a recent improvement toO(ϵ(21−√73)/8) =O(ϵ1.55) by Nisan and Impagliazzo. The New exponent yields an increased lower bound ofn(7−√3)/2−o(1)= Ω(n2.63) for the de Morgan formula size of a function in P defined by Andreev. This is the largest formula size lower bound known, even for functions in NP.
No takes yet. Share an insight, caveat, or question.
Paterson et al. (1993) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: