# RecurJac: An Efficient Recursive Algorithm for Bounding Jacobian Matrix of Neural Networks and Its Applications

arXiv: https://arxiv.org/abs/1810.11783 · HTML: https://mlsanity.com/paper/1810.11783/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2018.

## Built on by (most cited first, 27 of 27)

- [Skew Orthogonal Convolutions](https://mlsanity.com/paper/2105.11417/) (2021)
- [Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds](https://mlsanity.com/paper/2111.01395/) (2021)
- [Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100](https://mlsanity.com/paper/2108.04062/) (2021)
- [Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation](https://mlsanity.com/paper/2210.07394/) (2022)
- [Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration](https://mlsanity.com/paper/2305.16173/) (2023)
- [A Quantitative Geometric Approach to Neural-Network Smoothness](https://mlsanity.com/paper/2203.01212/) (2022)
- [RetrievalGuard: Provably Robust 1-Nearest Neighbor Image Retrieval](https://mlsanity.com/paper/2206.11225/) (2022)
- [Adversarial robustness of sparse local Lipschitz predictors](https://mlsanity.com/paper/2202.13216/) (2022)
- [Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks](https://mlsanity.com/paper/2102.13184/) (2021)
- [Fairness Properties of Face Recognition and Obfuscation Systems](https://mlsanity.com/paper/2108.02707/) (2021)
- [Improved techniques for deterministic l2 robustness](https://mlsanity.com/paper/2211.08453/) (2022)
- [CertViT: Certified Robustness of Pre-Trained Vision Transformers](https://mlsanity.com/paper/2302.10287/) (2023)
- [SpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalization](https://mlsanity.com/paper/2402.03317/) (2024)
- [Policy Verification in Stochastic Dynamical Systems Using Logarithmic Neural Certificates](https://mlsanity.com/paper/2406.00826/) (2024)
- [SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing](https://mlsanity.com/paper/2407.02811/) (2024)
- [Provable Bounds on the Hessian of Neural Networks: Derivative-Preserving Reachability Analysis](https://mlsanity.com/paper/2406.04476/) (2024)
- [An automatic differentiation system for the age of differential privacy](https://mlsanity.com/paper/2109.10573/) (2021)
- [Local Stability and Region of Attraction Analysis for Neural Network Feedback Systems under Positivity Constraints](https://mlsanity.com/paper/2505.22889/) (2025)
- [Certified Interpretability Robustness for Class Activation Mapping](https://mlsanity.com/paper/2301.11324/) (2023)
- [ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks](https://mlsanity.com/paper/2510.05261/) (2025)
- [Generative Model Adversarial Training for Deep Compressed Sensing](https://mlsanity.com/paper/2106.10696/) (2021)
- [STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformers](https://mlsanity.com/paper/2401.05338/) (2023)
- [Lipschitz-aware Linearity Grafting for Certified Robustness](https://mlsanity.com/paper/2510.25130/) (2025)
- [CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation](https://mlsanity.com/paper/2602.04856/) (2026)
- [Certified and accurate computation of function space norms of deep neural networks](https://mlsanity.com/paper/2603.06431/) (2026)
- [Demystifying Lipschitz verification: positive matrices, negative results](https://mlsanity.com/paper/2603.28113/) (2026)
- [Certified Mechanistic Interpretability: Lifting Single-Input Findings to Bounded Neighbourhoods](https://mlsanity.com/paper/2609.26112/) (2026)

## Abstract (arXiv)

The Jacobian matrix (or the gradient for single-output networks) is directly related to many important properties of neural networks, such as the function landscape, stationary points, (local) Lipschitz constants and robustness to adversarial attacks. In this paper, we propose a recursive algorithm, RecurJac, to compute both upper and lower bounds for each element in the Jacobian matrix of a neural network with respect to network's input, and the network can contain a wide range of activation functions. As a byproduct, we can efficiently obtain a (local) Lipschitz constant, which plays a crucial role in neural network robustness verification, as well as the training stability of GANs. Experiments show that (local) Lipschitz constants produced by our method is of better quality than previous approaches, thus providing better robustness verification results. Our algorithm has polynomial time complexity, and its computation time is reasonable even for relatively large networks. Additionally, we use our bounds of Jacobian matrix to characterize the landscape of the neural network, for example, to determine whether there exist stationary points in a local neighborhood. Source code available at urlhttp://github.com/huanzhang12/RecurJac-Jacobian-bounds.