Oblivious Complexity Classes Revisited: Lower Bounds and Hierarchies

Abstract: In this work we study oblivious complexity classes. These classes capture the power of interactive proofs where the prover(s) are only given the input size rather than the actual input. In particular, we study the connections between the symmetric polynomial time $\mathsf{S_2P}$ and its oblivious counterpart $\mathsf{O_2P}$. Among our results, we construct an explicit language in $\mathsf{O_2P}$ that cannot be computed by circuits of size $n^k$, and thus prove a hierarchy theorem for $\mathsf{O_2TIME}$. Along the way we also make partial progress towards the resolution of an open question posed by Goldreich and Meir (TOCT 2015) that relates the complexity of $\mathsf{NP}$ to its oblivious counterpart $\mathsf{ONP}$. To the best of our knowledge, these results constitute the first explicit fixed-polynomial lower bound and hierarchy theorem for $\mathsf{O_2P}$. The smallest uniform complexity class for which such lower bounds were previously known was $\mathsf{S_2P}$, due to Cai (JCSS 2007). In addition, this is the first uniform hierarchy theorem for a semantic class. All previous results required some non-uniformity.