English
Related papers

Related papers: Training Transformers with Enforced Lipschitz Cons…

200 papers

Effective hyper-parameter tuning is essential to guarantee the performance that neural networks have come to be known for. In this work, a principled approach to choosing the learning rate is proposed for shallow feedforward neural…

Machine Learning · Computer Science 2020-10-01 Thulasi Tholeti , Sheetal Kalyani

Deep transformer neural network models have improved the predictive accuracy of intelligent text processing systems in the biomedical domain. They have obtained state-of-the-art performance scores on a wide variety of biomedical and…

Computation and Language · Computer Science 2021-11-17 Milad Moradi , Matthias Samwald

Transformer architecture gradually dominates the LLM field. Recent advances in training optimization for Transformer-based large language models (LLMs) primarily focus on architectural modifications or optimizer adjustments. However, these…

This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks. Lipschitz regularity is now established as a key property of modern deep learning with implications in training stability, generalization,…

Machine Learning · Computer Science 2020-11-10 Alexandre Araujo , Benjamin Negrevergne , Yann Chevaleyre , Jamal Atif

Deep Neural Networks (DNNs) are vulnerable to adversarial attacks. Existing methods are devoted to developing various robust training strategies or regularizations to update the weights of the neural network. But beyond the weights, the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Minjing Dong , Yanxi Li , Yunhe Wang , Chang Xu

The monotonic dependence of the outputs of a neural network on some of its inputs is a crucial inductive bias in many scenarios where domain knowledge dictates such behavior. This is especially important for interpretability and fairness…

Machine Learning · Computer Science 2023-07-17 Ouail Kitouni , Niklas Nolte , Michael Williams

We present a comprehensive theoretical and empirical study of the Muon optimizer for training transformers only with a small to medium decoder (30M - 200M parameters), with an emphasis on its mathematical foundations, convergence properties…

Machine Learning · Computer Science 2025-09-30 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\epsilon$-robust, consume huge resources, they can only achieve small degree of robustness in…

Machine Learning · Computer Science 2018-11-21 Hajime Ono , Tsubasa Takahashi , Kazuya Kakizaki

Lipschitz constant is a fundamental property in certified robustness, as smaller values imply robustness to adversarial examples when a model is confident in its prediction. However, identifying the worst-case adversarial examples is known…

Machine Learning · Computer Science 2025-12-16 Yongjin Han , Suhyun Kim

Existing Rademacher complexity bounds for neural networks rely only on norm control of the weight matrices and depend exponentially on depth via a product of the matrix norms. Lower bounds show that this exponential dependence on depth is…

Machine Learning · Computer Science 2020-04-13 Colin Wei , Tengyu Ma

Robustness against unwanted perturbations is an important aspect of deploying neural network classifiers in the real world. Common natural perturbations include noise, saturation, occlusion, viewpoint changes, and blur deformations. All of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-19 Sadaf Gulshad , Ivan Sosnovik , Arnold Smeulders

Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input. The worst-case robustness against these so-called adversarial examples can be quantified by the Lipschitz…

Machine Learning · Statistics 2025-07-03 Paul Geuchen , Dominik Stöger , Thomas Telaar , Felix Voigtlaender

The Lipschitz bound, a technique from robust statistics, can limit the maximum changes in the output concerning the input, taking into account associated irrelevant biased factors. It is an efficient and provable method for examining the…

Machine Learning · Computer Science 2023-12-13 Yaning Jia , Chunhui Zhang

Certifiable robustness gives the guarantee that small perturbations around an input to a classifier will not change the prediction. There are two approaches to provide certifiable robustness to adversarial examples: a) explicitly training…

Machine Learning · Computer Science 2025-08-04 Meiyu Zhong , Ravi Tandon

The Transformer translation model employs residual connection and layer normalization to ease the optimization difficulties caused by its multi-layer encoder/decoder structure. Previous research shows that even with residual connection and…

Computation and Language · Computer Science 2020-05-06 Hongfei Xu , Qiuhui Liu , Josef van Genabith , Deyi Xiong , Jingyi Zhang

This paper introduces a new parameterization of deep neural networks (both fully-connected and convolutional) with guaranteed $\ell^2$ Lipschitz bounds, i.e. limited sensitivity to input perturbations. The Lipschitz guarantees are…

Machine Learning · Computer Science 2023-06-07 Ruigang Wang , Ian R. Manchester

Stability and robustness are critical for deploying Transformers in safety-sensitive settings. A principled way to enforce such behavior is to constrain the model's Lipschitz constant. However, approximation-theoretic guarantees for…

Machine Learning · Computer Science 2026-02-18 Takashi Furuya , Davide Murari , Carola-Bibiane Schönlieb

The Muon optimizer has received considerable attention for its strong performance in training large language models, yet the design principle behind its matrix-gradient orthogonalization remains largely elusive. In this paper, we introduce…

Optimization and Control · Mathematics 2026-04-03 Zhehang Du , Weijie Su

As deep neural networks (DNNs) are increasingly deployed in sensitive applications, ensuring their security and robustness has become critical. A major threat to DNNs arises from adversarial attacks, where small input perturbations can lead…

Machine Learning · Computer Science 2025-11-27 Erh-Chung Chen , Pin-Yu Chen , I-Hsin Chung , Che-Rung Lee

This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight…

Machine Learning · Computer Science 2017-12-06 Peter Bartlett , Dylan J. Foster , Matus Telgarsky