---
title: "A Formal Theory of Optimal Learning with Experimental Results"
authors:
  - "Michael Timothy Bennett"
doi: "10.24963/ijcai.2025/1238"
url: "https://ijcai.org/proceedings/2025/1238"
pdf: "https://ijcai.org/proceedings/2025/1238.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "10967-10968"
track: "Doctoral Consortium"
keywords:
  - "Search: S: Search and machine learning"
  - "Planning and Scheduling: PS: Other"
  - "Constraint Satisfaction and Optimization: CSO: Other"
  - "Search: S: Other"
  - "Machine Learning: ML: Learning theory"
---

# A Formal Theory of Optimal Learning with Experimental Results

Michael Timothy Bennett

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 10967-10968. DOI: [10.24963/ijcai.2025/1238](https://doi.org/10.24963/ijcai.2025/1238)

## Abstract

Here I summarise some results from my thesis which are relevant to artificial intelligence (AI) and machine learning (ML). The key contribution is a theory of optimally sample and energy efficient learning, which is supported by mathematical proofs and experimental results.