Towards Logical Specification of Statistical Machine Learning

Kawamoto, Yusuke

doi:10.1007/978-3-030-30446-1_16

Cited by 6 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using StatEL we introduced (α, n)-statistical secrecy with a significance level α and a sample size n, and showed that StatEL is useful to formalize hypothesis testing and differential privacy in a simple way. As shown in [24], StatEL can also express certain properties of statistical machine learning.…”

Section: Discussionmentioning

confidence: 99%

Statistical Epistemic Logic

Kawamoto

2019

The Art of Modelling Computational Systems: A Journey From Logic and Concurrency to Security and Privacy

Self Cite

View full text Add to dashboard Cite

We introduce a modal logic for describing statistical knowledge, which we call statistical epistemic logic. We propose a Kripke model dealing with probability distributions and stochastic assignments, and show a stochastic semantics for the logic. To our knowledge, this is the first semantics for modal logic that can express the statistical knowledge dependent on non-deterministic inputs and the statistical significance of observed results. By using statistical epistemic logic, we express a notion of statistical secrecy with a confidence level. We also show that this logic is useful to formalize statistical hypothesis testing and differential privacy in a simple and abstract manner.

show abstract

Section: Discussionmentioning

confidence: 99%

Statistical Epistemic Logic

Kawamoto

2019

The Art of Modelling Computational Systems: A Journey From Logic and Concurrency to Security and Privacy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Be that as it may, the work of Kawamoto (2019) leads to an account where fairness can be expressed as a logical property using predicates for protected attributes, remarkably similar in spirit to our approach if one were to ignore actions. This should, in the very least, suggest that such attempts are very promising, and for the future, it would be worthwhile to conduct a deeper investigation on how these formalization attempts can be synthesized to obtain a general probabilistic logical account that combines the strength of dynamic epistemic languages and statistical measures.…”

Section: Contributionsmentioning

confidence: 94%

Toward A Logical Theory Of Fairness and Bias

Belle¹

2023

Theory and Practice of Logic Programming

View full text Add to dashboard Cite

Fairness in machine learning is of considerable interest in recent years owing to the propensity of algorithms trained on historical data to amplify and perpetuate historical biases. In this paper, we argue for a formal reconstruction of fairness definitions, not so much to replace existing definitions but to ground their application in an epistemic setting and allow for rich environmental modeling. Consequently we look into three notions: fairness through unawareness, demographic parity and counterfactual fairness, and formalize these in the epistemic situation calculus.

show abstract

“…It is conducted at goal level without touching concrete functions of ML systems. In [11], a logical approach is given for specifying statistical properties of ML systems based on a Kripke model. It includes formal notations for robustness and fairness of classifiers, as well as relations among properties of classifiers.…”

Section: Related Workmentioning

confidence: 99%

A framework for Requirements specification of machine-learning systems

Wang¹

2022

Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

The rapid development of machine learning (ML) systems has raised many concerns over their quality. Due to the inherent complexity and uncertainty, most of the traditional quality assurance techniques have been challenged, including requirements specification. Current strategies mainly focus on model extraction from existing neural networks to improve interpretability and facilitate system analysis, but failing to include user expectations on the system. To handle the problem, this paper proposes a specification framework for ML requirements where each ML system is regarded as a set of snapshot systems along the evolvement process. There are 3 layers in the framework and the hierarchy indicates that higher-level models need to be built based on lower-level ones. The bottom layer consists of meta snapshot model and meta data model serving as the meta models for snapshot systems and data requirements respectively. The middle layer is for snapshot models each describing a snapshot system through relations between its outputs produced with different inputs. The top layer is a learning model capturing the evolvement process by transitions among snapshot models. These transitions are activated by data models instantiated from meta data model. We adopt the specification of a self-driving system to illustrate the framework.

show abstract

Towards Logical Specification of Statistical Machine Learning

Cited by 6 publications

References 32 publications

Statistical Epistemic Logic

Statistical Epistemic Logic

Toward A Logical Theory Of Fairness and Bias

A framework for Requirements specification of machine-learning systems

Contact Info

Product

Resources

About