paper-with-me

홈 › Papers

The Limits of AI Explainability: An Algorithmic Information Theory Approach

2025-04-29 · Shrisha Rao

This paper establishes a theoretical foundation for understanding the fundamental limits of AI explainability through algorithmic information theory. We formalize explainability as the approximation of complex models by simpler ones, quantifying both approximation error and explanation complexity using Kolmogorov complexity. Our key theoretical contributions include: (1) a complexity gap theorem proving that any explanation significantly simpler than the original model must differ from it on some inputs; (2) precise bounds showing that explanation complexity grows exponentially with input dimension but polynomially with error tolerance for Lipschitz functions; and (3) a characterization of the gap between local and global explainability, demonstrating that local explanations can be significantly simpler while maintaining accuracy in relevant regions. We further establish a regulatory impossibility theorem proving that no governance framework can simultaneously pursue unrestricted AI capabilities, human-interpretable explanations, and negligible error. These results highlight considerations likely to be relevant to the design, evaluation, and oversight of explainable AI systems.

📄 PDF Abstract BibTeX arXiv:2504.20676

Code (0)

등록된 구현이 없습니다.

Tasks

Automated Theorem Proving

Similar Papers 제목 키워드 기반

Information limits and Thouless-Anderson-Palmer equations for spiked matrix models with structured noise

2024-05-31 · Jean Barbier, Francesco Camilli, Marco Mondelli, Yizhou Xu

We consider a prototypical problem of Bayesian inference for a structured spiked model: a low-rank signal is corrupted by additive noise. While both information-theoretic and algorithmic limits are well understood when t…

Bayesian Inference

An Algorithmic Information-Theoretic Perspective on the Symbol Grounding Problem

2025-10-02 · Zhangchi Liu arxiv

This paper provides a definitive, unifying framework for the Symbol Grounding Problem (SGP) by reformulating it within Algorithmic Information Theory (AIT). We demonstrate that the grounding of meaning is a process funda…

Limits of Transfer Learning

2020-06-23 · Jake Williams, Abel Tadesse, Tyler Sam, Huey Sun 외

Transfer learning involves taking information and insight from one problem domain and applying it to a new problem domain. Although widely used in practice, theory for transfer learning remains less well-developed. To ad…

Transfer Learning

Explaining Machine Learning Models using Entropic Variable Projection

2018-10-18 · François Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes 외

In this paper, we present a new explainability formalism designed to shed light on how each input variable of a test set impacts the predictions of machine learning models. Hence, we propose a group explainability formal…

BIG-bench Machine Learning

Complexity Theory for Discrete Black-Box Optimization Heuristics

2018-01-06 · Carola Doerr

A predominant topic in the theory of evolutionary algorithms and, more generally, theory of randomized black-box optimization techniques is running time analysis. Running time analysis aims at understanding the performan…

Evolutionary Algorithms