Learning algorithms versus automatability of Frege systems

11/20/2021
by   Jan Pich, et al.
0

We connect learning algorithms and algorithms automating proof search in propositional proof systems: for every sufficiently strong, well-behaved propositional proof system P, we prove that the following statements are equivalent, 1. Provable learning: P proves efficiently that p-size circuits are learnable by subexponential-size circuits over the uniform distribution with membership queries. 2. Provable automatability: P proves efficiently that P is automatable by non-uniform circuits on propositional formulas expressing p-size circuit lower bounds. Here, P is sufficiently strong and well-behaved if I.-III. holds: I. P p-simulates Jeřábek's system WF (which strengthens the Extended Frege system EF by a surjective weak pigeonhole principle); II. P satisfies some basic properties of standard proof systems which p-simulate WF; III. P proves efficiently for some Boolean function h that h is hard on average for circuits of subexponential size. For example, if III. holds for P=WF, then Items 1 and 2 are equivalent for P=WF. If there is a function h∈ NE∩ coNE which is hard on average for circuits of size 2^n/4, for each sufficiently big n, then there is an explicit propositional proof system P satisfying properties I.-III., i.e. the equivalence of Items 1 and 2 holds for P.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/28/2020

Learning algorithms from circuit lower bounds

We revisit known constructions of efficient learning algorithms from var...
research
05/01/2023

An Approach to Circuit Lower Bounds via Bounded Width Circuits

In this paper, we investigate an approach to circuit lower bounds via bo...
research
03/19/2023

A proof complexity conjecture and the Incompleteness theorem

Given a sound first-order p-time theory T capable of formalizing syntax ...
research
02/12/2021

Proof complexity of positive branching programs

We investigate the proof complexity of systems based on positive branchi...
research
11/10/2018

Uniform, Integral and Feasible Proofs for the Determinant Identities

Aiming to provide weak as possible axiomatic assumptions in which one ca...
research
12/03/2020

Quantum learning algorithms imply circuit lower bounds

We establish the first general connection between the design of quantum ...
research
10/12/2011

The Language of Search

This paper is concerned with a class of algorithms that perform exhausti...

Please sign up or login with your details

Forgot password? Click here to reset