# Fuzzy PyTorch: Rapid Numerical Variability Evaluation for Deep Learning Models

arXiv: https://arxiv.org/abs/2605.25991 · HTML: https://mlsanity.com/paper/2605.25991/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 48 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 11 of 11)

- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [QuickNAT: A Fully Convolutional Network for Quick and Accurate Segmentation of Neuroanatomy](https://mlsanity.com/paper/1801.04161/) (2018)
- [TinyIREE: An ML Execution Environment for Embedded Systems from Compilation to Deployment](https://mlsanity.com/paper/2205.14479/) (2022)
- [DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning](https://mlsanity.com/paper/2202.03493/) (2022)
- [Mixed precision accumulation for neural network inference guided by componentwise forward error analysis](https://mlsanity.com/paper/2503.15568/) (2025)
- [Reducing numerical precision preserves classification accuracy in Mondrian Forests](https://mlsanity.com/paper/2106.14340/) (2021)
- [PyTracer: Automatically profiling numerical instabilities in Python](https://mlsanity.com/paper/2112.11508/) (2021)
- [Numerical Uncertainty of Convolutional Neural Networks Inference for Structural Brain MRI Analysis](https://mlsanity.com/paper/2308.01939/) (2023)
- [Conservative & Aggressive NaNs Accelerate U-Nets for Neuroimaging](https://mlsanity.com/paper/2601.17180/) (2026)

## Built on by (most cited first, 2 of 2)

- [Automated Numerical Stability Analysis of Deep Learning Operators](https://mlsanity.com/paper/2607.25494/) (2026)
- [Stochastic Rounding in Low-Precision Transformer Inference: A Variable-Precision Emulation Study of a Small GPT-2](https://mlsanity.com/paper/2610.01889/) (2026)

## Abstract (arXiv)

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.