Explainable AI via Learning to Optimize

TL;DR

This paper introduces a 'learn to optimize' framework for explainable AI that encodes prior knowledge, provides theoretical guarantees, and uses interpretable certificates to ensure trustworthy inferences across various applications.

Contribution

It presents a new L2O-based approach for XAI that is easy to implement, encodes prior knowledge, and offers theoretical and verification tools for trustworthy AI in practical tasks.

Findings

L2O models effectively encode prior knowledge.

The approach provides theoretical guarantees for constraints.

Numerical examples demonstrate practical effectiveness.

Abstract

Indecipherable black boxes are common in machine learning (ML), but applications increasingly require explainable artificial intelligence (XAI). The core of XAI is to establish transparent and interpretable data-driven algorithms. This work provides concrete tools for XAI in situations where prior knowledge must be encoded and untrustworthy inferences flagged. We use the "learn to optimize" (L2O) methodology wherein each inference solves a data-driven optimization problem. Our L2O models are straightforward to implement, directly encode prior knowledge, and yield theoretical guarantees (e.g. satisfaction of constraints). We also propose use of interpretable certificates to verify whether model inferences are trustworthy. Numerical examples are provided in the applications of dictionary-based signal recovery, CT imaging, and arbitrage trading of cryptoassets. Code and additional documentation can be found at https://xai-l2o.research.typal.academy.