Average-Case Lower Bounds and Satisfiability Algorithms for Small Threshold Circuits

06/16/2018
by   Ruiwen Chen, et al.
0

We show average-case lower bounds for explicit Boolean functions against bounded-depth threshold circuits with a superlinear number of wires. We show that for each integer d > 1, there is a constant ε_d > 0 such that the Parity function on n bits has correlation at most n^-ε_d with depth-d threshold circuits which have at most n^1+ε_d wires, and the Generalized Andreev function on n bits has correlation at most (-n^ε_d) with depth-d threshold circuits which have at most n^1+ε_d wires. Previously, only worst-case lower bounds in this setting were known (Impagliazzo, Paturi, and Saks (SICOMP 1997)). We use our ideas to make progress on several related questions. We give satisfiability algorithms beating brute force search for depth-d threshold circuits with a superlinear number of wires. These are the first such algorithms for depth greater than 2. We also show that Parity on n bits cannot be computed by polynomial-size AC^0 circuits with n^o(1) general threshold gates. Previously no lower bound for Parity in this setting could handle more than (n) gates. This result also implies subexponential-time learning algorithms for AC^0 with n^o(1) threshold gates under the uniform distribution. In addition, we give almost optimal bounds for the number of gates in a depth-d threshold circuit computing Parity on average, and show average-case lower bounds for threshold formulas of any depth. Our techniques include adaptive random restrictions, anti-concentration and the structural theory of linear threshold functions, and bounded-read Chernoff bounds.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset