Stochastic Perturbations of Tabular Features for Non-Deterministic Inference with Automunge

TL;DR

This paper explores injecting stochastic noise into tabular features during inference to induce non-determinism, with the Automunge library supporting various noise methods and quantum integration for enhanced robustness and fairness.

Contribution

It introduces a novel approach to non-deterministic inference using noise injection and quantum techniques, supported by the Automunge library.

Findings

Provides methods for stochastic feature perturbation during inference.

Demonstrates integration of quantum circuits for entropy seeding.

Highlights potential benefits for fairness and adversarial robustness.

Abstract

Injecting gaussian noise into training features is well known to have regularization properties. This paper considers noise injections to numeric or categoric tabular features as passed to inference, which translates inference to a non-deterministic outcome and may have relevance to fairness considerations, adversarial example protection, or other use cases benefiting from non-determinism. We offer the Automunge library for tabular preprocessing as a resource for the practice, which includes options to integrate random sampling or entropy seeding with the support of quantum circuits, representing a new way to channel quantum algorithms into classical learning.