We consider the approximability of constraint satisfaction problems in the streaming setting. For every constraint satisfaction problem (CSP) on $n$ variables taking values in ${0,ldots,q-1}$, we prove that improving over the trivial approximability
by a factor of $q$ requires $Omega(n)$ space even on instances with $O(n)$ constraints. We also identify a broad subclass of problems for which any improvement over the trivial approximability requires $Omega(n)$ space. The key technical core is an optimal, $q^{-(k-1)}$-inapproximability for the case where every constraint is given by a system of $k-1$ linear equations $bmod; q$ over $k$ variables. Prior to our work, no such hardness was known for an approximation factor less than $1/2$ for any CSP. Our work builds on and extends the work of Kapralov and Krachun (Proc. STOC 2019) who showed a linear lower bound on any non-trivial approximation of the max cut in graphs. This corresponds roughly to the case of Max $k$-LIN-$bmod; q$ with $k=q=2$. Each one of the extensions provides non-trivial technical challenges that we overcome in this work.
A constraint satisfaction problem (CSP), Max-CSP$({cal F})$, is specified by a finite set of constraints ${cal F} subseteq {[q]^k to {0,1}}$ for positive integers $q$ and $k$. An instance of the problem on $n$ variables is given by $m$ applications o
f constraints from ${cal F}$ to subsequences of the $n$ variables, and the goal is to find an assignment to the variables that satisfies the maximum number of constraints. In the $(gamma,beta)$-approximation version of the problem for parameters $0 leq beta < gamma leq 1$, the goal is to distinguish instances where at least $gamma$ fraction of the constraints can be satisfied from instances where at most $beta$ fraction of the constraints can be satisfied. In this work we consider the approximability of this problem in the context of streaming algorithms and give a dichotomy result in the dynamic setting, where constraints can be inserted or deleted. Specifically, for every family ${cal F}$ and every $beta < gamma$, we show that either the approximation problem is solvable with polylogarithmic space in the dynamic setting, or not solvable with $o(sqrt{n})$ space. We also establish tight inapproximability results for a broad subclass in the streaming insertion-only setting. Our work builds on, and significantly extends previous work by the authors who consider the special case of Boolean variables ($q=2$), singleton families ($|{cal F}| = 1$) and where constraints may be placed on variables or their negations. Our framework extends non-trivially the previous work allowing us to appeal to richer norm estimation algorithms to get our algorithmic results. For our negative results we introduce new variants of the communication problems studied in the previous work, build new reductions for these problems, and extend the technical parts of previous works.
A Boolean constraint satisfaction problem (CSP), Max-CSP$(f)$, is a maximization problem specified by a constraint $f:{-1,1}^kto{0,1}$. An instance of the problem consists of $m$ constraint applications on $n$ Boolean variables, where each constraint
application applies the constraint to $k$ literals chosen from the $n$ variables and their negations. The goal is to compute the maximum number of constraints that can be satisfied by a Boolean assignment to the $n$~variables. In the $(gamma,beta)$-approximation version of the problem for parameters $gamma geq beta in [0,1]$, the goal is to distinguish instances where at least $gamma$ fraction of the constraints can be satisfied from instances where at most $beta$ fraction of the constraints can be satisfied. In this work we consider the approximability of Max-CSP$(f)$ in the (dynamic) streaming setting, where constraints are inserted (and may also be deleted in the dynamic setting) one at a time. We completely characterize the approximability of all Boolean CSPs in the dynamic streaming setting. Specifically, given $f$, $gamma$ and $beta$ we show that either (1) the $(gamma,beta)$-approximation version of Max-CSP$(f)$ has a probabilistic dynamic streaming algorithm using $O(log n)$ space, or (2) for every $varepsilon > 0$ the $(gamma-varepsilon,beta+varepsilon)$-approximation version of Max-CSP$(f)$ requires $Omega(sqrt{n})$ space for probabilistic dynamic streaming algorithms. We also extend previously known results in the insertion-only setting to a wide variety of cases, and in particular the case of $k=2$ where we get a dichotomy and the case when the satisfying assignments of $f$ support a distribution on ${-1,1}^k$ with uniform marginals.
