DASH
Repository logo
Communities & Collections
Browse DASH
DASH Stories
Statistics
  1. Home
  2. Faculty of Arts and Sciences
  3. FAS Theses and Dissertations
  4. Epistemic Limits of Trustworthy Machine Learning

Epistemic Limits of Trustworthy Machine Learning

Open/View files
Epistemic_Limits_of_Trustworthy_Machine_Learning.pdf (4.8 MB)
Date
August 5, 2025
Author(s)
Monteiro Paes, Lucas W.
The Harvard community has made this article openly available. Please share how this access benefits you.
Citation
Monteiro Paes, Lucas W.. 2025. Epistemic Limits of Trustworthy Machine Learning. Doctoral Dissertation, Harvard University Graduate School of Arts and Sciences.
Abstract
Theoretical understanding of a system’s limits has long driven technological breakthroughs. Carnot delineated the fundamental limits of heat engine efficiency, paving the way for the design of modern state-of-the-art engines. More than a century later, Claude Shannon unraveled the fundamental limit of communication, known as channel capacity. This insight revolutionized communication systems, enabling continual improvements that ultimately led to wireless communication as we know it today. This thesis discusses the epistemic limits of machine learning (ML) and leverages them to improve the trustworthiness of ML systems. ML models have an epistemic limit when proving one of their properties is impossible. Epistemic refers to the impossibility of providing theoretical guarantees (knowledge) about a model's property. Epistemic limits are information-theoretic converse results on the hypothesis test that checks a model's property. First, we prove a limit on how much information personalized models can use while ensuring reliable test for performance gains across all users -- epistemic limits of personalization. We leverage this limit to develop a tool to help with feature selection. Second, we show a limit for reliably testing if model performance is equitable across multiple demographic groups --epistemic limit of fairness testing. We exploit this limit to design a metric for efficient algorithmic bias detection. Third, we prove a limit for testing if one model outperforms another on average -- epistemic limit of model selection. We use this result to delineate the set of indistinguishably good models --Rashomon set. Finally, we argue that the epistemic limits in model selection imply that explaining the predictions of ML models is necessary. Then, we develop efficient methods for explaining the content produced by large language models.
Terms of Use
This article is made available under the terms and conditions applicable to Other Posted Material (LAA), as set forth at Terms of Service
URI
https://dash.harvard.edu/handle/1/42725112
Subjects

Artificial Inteligenc...

Explainability

Fairness

Hypothesis Testing

Information Theory

Predictive Multiplici...

Applied mathematics

Statistics

Artificial intelligen...

Collection
FAS Theses and Dissertations
Metrics
Repository logo
  • CONTACT US
  • OSRDS
  • ABOUT DASH
  • DEPOSITING TO DASH
  • TERMS OF USE
  • REQUEST A WAIVER
  • TAKE DOWN POLICY
  • NAME CHANGE POLICY
  • HARVARD OA POLICIES
  • DASH SUBMITTER AGREEMENT
  • Accessibility
  • Privacy
Creative Commons License BY
Creative Commons Attribution 4.0 International License

Except where otherwise noted, this work is subject to a Creative Commons Attribution 4.0 International License,
which allows anyone to share and adapt our material as long as proper attribution is given.
For details and exceptions, see the Harvard Library Copyright Policy
©2024 Presidents and Fellows of Harvard College.