Online Orthogonal Vectors Revisited

We prove new upper and lower bounds for the Online Orthogonal Vectors Problem (OnlineOV n,d ). In this problem, a preprocessing algorithm receives n vectors x 1 , . . . , x n ∈ 0, 1 d and constructs a data structure of size S. A query algorithm subsequently receives a query vector q ∈ 0, 1 d and in time T decides whether q is orthogonal to any of the input vectors x i .

We design a new deterministic data structure for OnlineOV n,d . In low dimensions (d = c log n), our data structure matches the performance of the best known randomized algorithm due to Chan [SoCG 2017]. Furthermore, in moderate dimensions (d = n ε ), we give the first improvement since Charikar, Indyk and Panigrahy [ICALP 2002]. Along the way, we give the first deterministic refutation of a conjecture on the hardness of OnlineOV posed by Goldstein, Lewenstein and Porat [ISAAC 2017]. This data structure also extends to a number of problems, including Partial Match, Orthogonal Range Search, and DNF Evaluation. We use a novel structure-versus-randomness decomposition to design our algorithm.

Under the Non-Uniform Strong Exponential Time Hypothesis, we also prove arbitrarily large polynomial space lower bounds for any OnlineOV data structure with sublinear query time even with computationally unbounded preprocessing. These lower bounds extend to several other problems, including Polynomial Evaluation, Partial Match, Orthogonal Range Search, and Approximate Nearest Neighbors. We also prove similar lower bounds for 3-SUM with preprocessing under the Non-Uniform Hamiltonian Path Conjecture.