A Fixed-Depth Size-Hierarchy Theorem for AC^0[⊕] via the Coin Problem

09/11/2018
by   Nutan Limaye, et al.
0

We prove the first Fixed-depth Size-hierarchy Theorem for uniform AC^0[⊕] circuits; in particular, for fixed d, the class C_d,k of uniform AC^0[⊕] formulas of depth d and size n^k form an infinite hierarchy. For this, we find the first class of explicit functions giving (up to polynomial factor) matching upper and lower bounds for AC^0[⊕] formulas, derived from the δ-Coin Problem, the computational problem of distinguishing between coins that are heads with probability (1+δ)/2 or (1-δ)/2, where δ is a parameter going to 0. We study this problem's complexity and make progress on both upper bounds and lower bounds. Upper bounds. We find explicit monotone AC^0 formulas solving the δ-coin problem, having depth d, size (O(d(1/δ)^1/(d-1))), and sample complexity poly(1/δ), for constant d>2. This matches previous upper bounds of O'Donnell and Wimmer (ICALP 2007) and Amano (ICALP 2009) in terms of size and improves the sample complexity. Lower bounds. The upper bounds are nearly tight even for the stronger model of AC^0[⊕] formulas (which allow NOT and Parity gates): any AC^0[⊕] formula solving the δ-coin problem must have size (Ω(d(1/δ)^1/(d-1))). This strengthens a result of Cohen, Ganor and Raz (APPROX-RANDOM 2014), who prove a similar result for AC^0, and a result of Shaltiel and Viola (SICOMP 2010), who give a superpolynomially weaker (still exponential) lower bound. The upper bound is a derandomization involving a use of Janson's inequality (as far as we know, the first such use of the inequality) and classical combinatorial designs. For the lower bound, we prove an optimal (up to constant factor) degree lower bound for multivariate polynomials over F_2 solving the δ-coin problem, which may be of independent interest.

READ FULL TEXT
research
09/11/2018

The Coin Problem in Constant Depth: Sample Complexity and Parity Gates

The δ-Coin Problem is the computational problem of distinguishing betwee...
research
05/02/2022

Improved Low-Depth Set-Multilinear Circuit Lower Bounds

We prove strengthened lower bounds for constant-depth set-multilinear fo...
research
02/21/2022

Defining long words succinctly in FO and MSO

We consider the length of the longest word definable in FO and MSO via a...
research
05/20/2022

Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search

Greedy best-first search (GBFS) and A* search (A*) are popular algorithm...
research
03/14/2021

Sharp indistinguishability bounds from non-uniform approximations

We study the problem of distinguishing between two symmetric probability...
research
07/13/2023

An Improved Uniform Convergence Bound with Fat-Shattering Dimension

The fat-shattering dimension characterizes the uniform convergence prope...
research
02/07/2019

Bounds for the VC Dimension of 1NN Prototype Sets

In Statistical Learning, the Vapnik-Chervonenkis (VC) dimension is an im...

Please sign up or login with your details

Forgot password? Click here to reset