MIT researchers claim their probabilistic programming language can assess the fairness of AI algorithms.
Algorithms are recognized to potentially have built-in bias. MIT researchers developed a new artificial intelligence programming language to assess the fairness of algorithms more exactly, and more quickly.
MIT’s Sum-Product Probabilistic Language (SPPL) is a probabilistic programming system that aims to make AI systems much easier to develop, with early successes in computer vision, common-sense data cleaning, and automated data modeling. Probabilistic programming languages work backward to infer probable explanations for observed data.
This system is not the first, but it delivers solutions thousands of times faster, claimed Feras Saad, a PhD student in electrical engineering and computer science (EECS) and first author on a recent paper describing the work. The system is said to be up to 3,000 times faster than previous approaches.
SPPL only allows users to write probabilistic programs for which it can automatically deliver exact probabilistic inference results. SPPL also makes it possible for users to check how fast inference will be. Error from approximate probabilistic inference is tolerable in many AI applications but corrupts results in socially impactful applications of AI, such as automated decision-making, and especially in fairness analysis.
SPPL avoids errors by restricting to a carefully designed class of models that still includes a broad class of AI algorithms, including the decision tree classifiers that are widely used for algorithmic decision-making. SPPL works by compiling probabilistic programs into a specialized data structure called a “sum-product expression.” SPPL further builds on the emerging theme of using probabilistic circuits as a representation enabling efficient probabilistic inference. SPPL is implemented in Python and is available open source.
Original Source: MIT