Luby--Veli\v{c}kovi\'c--Wigderson revisited: Improved correlation bounds and pseudorandom generators for depth-two circuits

TL;DR

This paper improves pseudorandom generators and correlation bounds for depth-two circuits with symmetric or threshold gates fed by AND gates, advancing derandomization techniques and circuit complexity understanding.

Contribution

It presents the first strict improvement over LVW93's seed length for PRGs targeting these circuits, using a new multi-switching lemma.

Findings

New PRG with seed length 2^{O(√log S)} + polylog(1/ε)

Enhanced correlation bounds for depth-two circuits with symmetric or threshold gates

Strengthened results for constant-depth circuits with multiple SYM or THR gates

Abstract

We study correlation bounds and pseudorandom generators for depth-two circuits that consist of a $\mathsf{SYM}$-gate (computing an arbitrary symmetric function) or $\mathsf{THR}$-gate (computing an arbitrary linear threshold function) that is fed by $S$ $\mathsf{AND}$ gates. Such circuits were considered in early influential work on unconditional derandomization of Luby, Veli\v{c}kovi\'c, and Wigderson [LVW93], who gave the first non-trivial PRG with seed length $2^{O(\sqrt{\log(S/\varepsilon)})}$ that $\varepsilon$-fools these circuits. In this work we obtain the first strict improvement of [LVW93]'s seed length: we construct a PRG that $\varepsilon$-fools size-$S$ $\{\mathsf{SYM},\mathsf{THR}\} \circ\mathsf{AND}$ circuits over $\{0,1\}^n$ with seed length \[ 2^{O(\sqrt{\log S })} + \mathrm{polylog}(1/\varepsilon), \] an exponential (and near-optimal) improvement of the $\varepsilon$-dependence of [LVW93]. The above PRG is actually a special case of a more general PRG which we establish for constant-depth circuits containing multiple $\mathsf{SYM}$ or $\mathsf{THR}$ gates, including as a special case $\{\mathsf{SYM},\mathsf{THR}\} \circ \mathsf{AC^0}$ circuits. These more general results strengthen previous results of Viola [Vio06] and essentially strengthen more recent results of Lovett and Srinivasan [LS11]. Our improved PRGs follow from improved correlation bounds, which are transformed into PRGs via the Nisan--Wigderson "hardness versus randomness" paradigm [NW94]. The key to our improved correlation bounds is the use of a recent powerful \emph{multi-switching} lemma due to H{\aa}stad [H{\aa}s14].