Undecidability of Learnability

06/02/2021
by   Matthias C. Caro, et al.
15

Machine learning researchers and practitioners steadily enlarge the multitude of successful learning models. They achieve this through in-depth theoretical analyses and experiential heuristics. However, there is no known general-purpose procedure for rigorously evaluating whether newly proposed models indeed successfully learn from data. We show that such a procedure cannot exist. For PAC binary classification, uniform and universal online learning, and exact learning through teacher-learner interactions, learnability is in general undecidable, both in the sense of independence of the axioms in a formal system and in the sense of uncomputability. Our proofs proceed via computable constructions of function classes that encode the consistency problem for formal systems and the halting problem for Turing machines into complexity measures that characterize learnability. Our work shows that undecidability appears in the theoretical foundations of machine learning: There is no one-size-fits-all algorithm for deciding whether a machine learning model can be successful. We cannot in general automatize the process of assessing new learning models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/24/2021

On computable learning of continuous features

We introduce definitions of computable PAC learning for binary classific...
research
08/20/2018

PAC-learning is Undecidable

The problem of attempting to learn the mapping between data and labels i...
research
10/12/2018

A Model for Auto-Programming for General Purposes

The Universal Turing Machine (TM) is a model for VonNeumann computers --...
research
05/04/2010

Informal Concepts in Machines

This paper constructively proves the existence of an effective procedure...
research
12/31/2021

High Dimensional Optimization through the Lens of Machine Learning

This thesis reviews numerical optimization methods with machine learning...
research
06/27/2023

Generating Elementary Integrable Expressions

There has been an increasing number of applications of machine learning ...
research
06/30/2018

chemmodlab: A Cheminformatics Modeling Laboratory for Fitting and Assessing Machine Learning Models

The goal of chemmodlab is to streamline the fitting and assessment pipel...

Please sign up or login with your details

Forgot password? Click here to reset