Learning Multiple Secrets in Mastermind

TL;DR

This paper introduces efficient algorithms and bounds for learning hidden subsets in high-dimensional spaces through adaptive queries, advancing understanding of query complexity in generalized Mastermind problems.

Contribution

It provides a two-round adaptive algorithm with near-optimal query complexity for the generalized Mastermind problem and establishes lower bounds on the number of rounds needed for learning.

Findings

Two-round adaptive algorithm with $ ilde{O}( ext{exp}( oot{2}\sqrt{d ext{log} n}))$ queries.

Lower bounds showing exponential query requirements for multi-round algorithms.

An $O(n^{d/2})$ query deterministic algorithm for the continuous variant.

Abstract

In the Generalized Mastermind problem, there is an unknown subset $H$ of the hypercube $\{0,1\}^d$ containing $n$ points. The goal is to learn $H$ by making a few queries to an oracle, which, given a point $q$ in $\{0,1\}^d$, returns the point in $H$ nearest to $q$. We give a two-round adaptive algorithm for this problem that learns $H$ while making at most $\exp(\tilde{O}(\sqrt{d \log n}))$ queries. Furthermore, we show that any $r$-round adaptive randomized algorithm that learns $H$ with constant probability must make $\exp(\Omega(d^{3^{-(r-1)}}))$ queries even when the input has $\text{poly}(d)$ points; thus, any $\text{poly}(d)$ query algorithm must necessarily use $\Omega(\log \log d)$ rounds of adaptivity. We give optimal query complexity bounds for the variant of the problem where queries are allowed to be from $\{0,1,2\}^d$. We also study a continuous variant of the problem in which $H$ is a subset of unit vectors in $\mathbb{R}^d$, and one can query unit vectors in $\mathbb{R}^d$. For this setting, we give an $O(n^{d/2})$ query deterministic algorithm to learn the hidden set of points.