Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models
Provides a scalable and efficient tool for researchers and practitioners to quantify floating-point uncertainty in deep learning models, addressing a practical need for robustness.
Fuzzy PyTorch integrates stochastic arithmetic into PyTorch to evaluate numerical variability in deep learning models, achieving 5x to 60x runtime reductions compared to Verrou while maintaining model performance across architectures from 1 to 341 million parameters.
We introduce Fuzzy PyTorch, a framework for rapid evaluation of numerical variability in deep learning (DL) models. As DL is increasingly applied to diverse tasks, understanding variability from floating-point arithmetic is essential to ensure robust and reliable performance. Tools assessing such variability must be scalable, efficient, and integrate seamlessly with existing frameworks while minimizing code modifications. Fuzzy PyTorch enables this by integrating stochastic arithmetic into PyTorch through Probabilistic Rounding with Instruction Set Management, a novel library interfacing with Verificarlo, a numerical analysis compiler. The library offers stochastic rounding mode and a novel mode; up-down rounding. Comparative evaluations show Fuzzy PyTorch maintains model performance and achieves runtime reductions of 5x to 60x versus Verrou, a state-of-the-art tool. We further demonstrate scalability by running models from 1 to 341 million parameters, confirming applicability across small and large DL architectures. Overall, Fuzzy PyTorch provides an efficient, scalable, and practical solution for assessing numerical variability in deep learning, enabling researchers and practitioners to quantify and manage floating-point uncertainty without compromising performance or computational efficiency.