mlsanityData to 14 Oct 2026

A Computability Perspective on (Verified) Machine Learning

arXiv 2102.06585 ↗First posted 12 Feb 2021cs.LG cs.LOcited by 3

Not on the map. Why?

Abstract (arXiv)

There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 16 of its 37 references that are in the map. First posted on arXiv 12 Feb 2021.

Builds on

16 of 37 references.

References · 16

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  5. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  6. 2016Safety Verification of Deep Neural Networkscited by 263
  7. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  8. 2017Feature-Guided Black-Box Safety Testing of Deep Neural Networkscited by 49
  9. 2018Geometry-Based Data Generationcited by 11
  10. 2017Weihrauch Complexity in Computable Analysiscited by 4
  11. 2014Point degree spectra of represented spacescited by 1
  12. 2016Noetherian Quasi-Polish Spacescited by 1
4 more
  1. 2019Overt choicecited by 1
  2. 2019Effective local compactness and the hyperspace of located setscited by 1
  3. 2020Decision problems for linear recurrences involving arbitrary real numberscited by 1
  4. 2021Adaptive Neighbourhoods for the Discovery of Adversarial Examplescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 0; 2023: 0; 2024: 0; 2025: 0; 2026: 1.

3 papers.

  1. 2021From Undecidability of Non-Triviality and Finiteness to Undecidability of Learnabilitycited by 4
  2. 2021On computable learning of continuous featurescited by 2
  3. 2026Uniform Computability of PAC Learningcited by 0