Learning Nearest-Neighbor Maps from Adaptive Queries

Abstract

We study the problem of learning nearest-neighbor maps from adaptive queries, which is equivalent to the following problem of reconstructing a hidden set $H$ via a nearest-neighbor query oracle. Let $K \subset \mathbb{R}^d$ be a compact domain in a normed space $(\mathbb{R}^d,\| \cdot\|)$ and let $H \subset K$ be a hidden set of $n$ points. Upon querying $q \in K$, the oracle returns some $h \in H$ with minimum distance from $q$. How many queries are required to exactly recover $H$? Previous work has studied this question in specific domains, namely the Boolean hypercube and the $\ell_2$-unit sphere. We generalize previous work and prove the tight worst-case query complexity bound of $Θ(nκ)$, where $κ$ is the kissing number of the underlying norm. In the Euclidean norm, obtaining tight asymptotic bounds on $κ$ is a significant open question, although it is known that $κ= \exp(Θ(d))$. Our second set of results shows that an exponential dependence on $d$ is required even in natural Euclidean domains: $\exp(Ω(d))$ queries are needed in the ball, even when $n=2$, and $n\exp(Ω(d))$ queries are needed in the cone. Lastly, we prove a sharper upper bound in the Euclidean sphere. Here, $d$ can be replaced by $\min(n,d)$ via a dimension reduction preprocessing step. This is a randomized version of a procedure due to Prabhu-Woodruff (ICML 2024) where we improve the query complexity from $O(nd)$ to $O(\min(n,d))$. This reveals a striking contrast between the sphere and the ball: when $n = O(1)$, the sphere admits an $O(1)$ query algorithm, whereas the ball requires $\exp(Ω(d))$.