Training Compute Thresholds: Features and Functions in AI Governance
- URL: http://arxiv.org/abs/2405.10799v1
- Date: Fri, 17 May 2024 14:10:24 GMT
- Title: Training Compute Thresholds: Features and Functions in AI Governance
- Authors: Lennart Heim,
- Abstract summary: We argue that compute thresholds serve as a valuable trigger for further evaluation of AI models.
Compute thresholds provide a practical starting point for identifying potentially high-risk models.
- Score: 0.8547032097715571
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: This paper examines the use of training compute thresholds as a tool for governing artificial intelligence (AI) systems. We argue that compute thresholds serve as a valuable trigger for further evaluation of AI models, rather than being the sole determinant of the regulation. Key advantages of compute thresholds include their correlation with model capabilities and risks, quantifiability, ease of measurement, robustness to circumvention, knowability before model development and deployment, potential for external verification, and targeted scope. Compute thresholds provide a practical starting point for identifying potentially high-risk models and can be used as an initial filter in AI governance frameworks alongside other sector-specific regulations and broader governance measures.
Related papers
- Computing Power and the Governance of Artificial Intelligence [51.967584623262674]
Governments and companies have started to leverage compute as a means to govern AI.
compute-based policies and technologies have the potential to assist in these areas, but there is significant variation in their readiness for implementation.
naive or poorly scoped approaches to compute governance carry significant risks in areas like privacy, economic impacts, and centralization of power.
arXiv Detail & Related papers (2024-02-13T21:10:21Z) - Mathematical Algorithm Design for Deep Learning under Societal and
Judicial Constraints: The Algorithmic Transparency Requirement [65.26723285209853]
We derive a framework to analyze whether a transparent implementation in a computing model is feasible.
Based on previous results, we find that Blum-Shub-Smale Machines have the potential to establish trustworthy solvers for inverse problems.
arXiv Detail & Related papers (2024-01-18T15:32:38Z) - Estimating Fr\'echet bounds for validating programmatic weak supervision [50.13475056199486]
We develop methods for estimating Fr'eche's bounds on (possibly high-dimensional) distribution classes in which some variables are continuous-valued.
We demonstrate the usefulness of our algorithms by evaluating the performance of machine learning (ML) models trained with programmatic weak supervision (PWS)
arXiv Detail & Related papers (2023-12-07T07:15:11Z) - Towards Explainable AI for Channel Estimation in Wireless Communications [1.0874597293913013]
The aim of the proposed XAI-CHEST scheme is to identify the relevant model inputs by inducing high noise on the irrelevant ones.
As a result, the behavior of the studied DL-based channel estimators can be further analyzed and evaluated.
arXiv Detail & Related papers (2023-07-03T11:51:00Z) - Modelling Assessment Rubrics through Bayesian Networks: a Pragmatic
Approach [59.77710485234197]
This paper presents an approach to deriving a learner model directly from an assessment rubric.
We illustrate how the approach can be applied to automatize the human assessment of an activity developed for testing computational thinking skills.
arXiv Detail & Related papers (2022-09-07T10:09:12Z) - Differential Assessment of Black-Box AI Agents [29.98710357871698]
We propose a novel approach to differentially assess black-box AI agents that have drifted from their previously known models.
We leverage sparse observations of the drifted agent's current behavior and knowledge of its initial model to generate an active querying policy.
Empirical evaluation shows that our approach is much more efficient than re-learning the agent model from scratch.
arXiv Detail & Related papers (2022-03-24T17:48:58Z) - Logic Constraints to Feature Importances [17.234442722611803]
"Black box" nature of AI models is often a limit for a reliable application in high-stakes fields like diagnostic techniques, autonomous guide, etc.
Recent works have shown that an adequate level of interpretability could enforce the more general concept of model trustworthiness.
The basic idea of this paper is to exploit the human prior knowledge of the features' importance for a specific task, in order to coherently aid the phase of the model's fitting.
arXiv Detail & Related papers (2021-10-13T09:28:38Z) - Unifying Gradient Estimators for Meta-Reinforcement Learning via
Off-Policy Evaluation [53.83642844626703]
We provide a unifying framework for estimating higher-order derivatives of value functions, based on off-policy evaluation.
Our framework interprets a number of prior approaches as special cases and elucidates the bias and variance trade-off of Hessian estimates.
arXiv Detail & Related papers (2021-06-24T15:58:01Z) - Evaluating the Safety of Deep Reinforcement Learning Models using
Semi-Formal Verification [81.32981236437395]
We present a semi-formal verification approach for decision-making tasks based on interval analysis.
Our method obtains comparable results over standard benchmarks with respect to formal verifiers.
Our approach allows to efficiently evaluate safety properties for decision-making models in practical applications.
arXiv Detail & Related papers (2020-10-19T11:18:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.