On the Parameterized Complexity of Learning Logic

02/24/2021
by   Steffen van Bergerem, et al.
0

We analyse the complexity of learning first-order definable concepts in a model-theoretic framework for supervised learning introduced by (Grohe and Turán, TOCS 2004). Previous research on the complexity of learning in this framework focussed on the question of when learning is possible in time sublinear in the background structure. Here we study the parameterized complexity of the learning problem. We obtain a hardness result showing that exactly learning first-order definable concepts is at least as hard as the corresponding model-checking problem, which implies that on general structures it is hard for the parameterized complexity class AW[*]. Our main contribution is a fixed-parameter tractable agnostic PAC learning algorithm for first-order definable concepts over effectively nowhere dense background structures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/19/2023

On the Parameterized Complexity of Learning Monadic Second-Order Formulas

Within the model-theoretic framework for supervised learning introduced ...
research
09/20/2021

A Parameterized View on the Complexity of Dependence Logic

In this paper, we investigate the parameterized complexity of model chec...
research
02/17/2022

Extended MSO Model Checking via Small Vertex Integrity

We study the model checking problem of an extended 𝖬𝖲𝖮 with local and gl...
research
08/22/2023

Consistency-Checking Problems: A Gateway to Parameterized Sample Complexity

Recently, Brand, Ganian and Simonov introduced a parameterized refinemen...
research
09/09/2019

Learning Concepts Definable in First-Order Logic with Counting

We study classification problems over relational background structures f...
research
09/22/2020

Learning Concepts Described by Weight Aggregation Logic

We consider weighted structures, which extend ordinary relational struct...
research
03/06/2018

On the parameterized complexity of manipulating Top Trading Cycles

We study the problem of exchange when 1) agents are endowed with heterog...

Please sign up or login with your details

Forgot password? Click here to reset