English
Related papers

Related papers: Approximation Theory for Lipschitz Continuous Tran…

200 papers

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

With the attention mechanism, transformers achieve significant empirical successes. Despite the intuitive understanding that transformers perform relational inference over long sequences to produce desirable representations, we lack a…

Machine Learning · Computer Science 2024-04-02 Yufeng Zhang , Boyi Liu , Qi Cai , Lingxiao Wang , Zhaoran Wang

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…

Machine Learning · Computer Science 2026-02-25 Wei Wang , Xiao-Yong Wei , Qing Li

Understanding the training dynamics of transformers is important to explain the impressive capabilities behind large language models. In this work, we study the dynamics of training a shallow transformer on a task of recognizing…

Machine Learning · Computer Science 2024-10-15 Hongru Yang , Bhavya Kailkhura , Zhangyang Wang , Yingbin Liang

One of the most influential results in neural network theory is the universal approximation theorem [1, 2, 3] which states that continuous functions can be approximated to within arbitrary accuracy by single-hidden-layer feedforward neural…

Machine Learning · Computer Science 2021-12-16 Clemens Hutter , Recep Gül , Helmut Bölcskei

The Latent Block Model (LBM) is a model-based method to cluster simultaneously the $d$ columns and $n$ rows of a data matrix. Parameter estimation in LBM is a difficult and multifaceted problem. Although various estimation strategies have…

Statistics Theory · Mathematics 2020-02-26 Vincent Brault , Christine Keribin , Mahendra Mariadassou

This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks based upon non-Euclidean contraction theory. The basic idea is to cast the robustness analysis of a neural…

Machine Learning · Computer Science 2022-08-09 Saber Jafarpour , Alexander Davydov , Matthew Abate , Francesco Bullo , Samuel Coogan

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

Transformers based on the attention mechanism have achieved impressive success in various areas. However, the attention mechanism has a quadratic complexity, significantly impeding Transformers from dealing with numerous tokens and scaling…

Machine Learning · Computer Science 2022-06-17 Haixu Wu , Jialong Wu , Jiehui Xu , Jianmin Wang , Mingsheng Long

We investigate the stabilisation of nominally linear-affine switched systems with uncertain Lipschitz nonlinearities under dwell-time constraints, using a sampled-data switching law based on a state observer. We design the switching law…

Optimization and Control · Mathematics 2026-04-29 Rami Katz , Antonio Russo , Gian Paolo Incremona , Patrizio Colaneri , Giulia Giordano

Transformers are state-of-the-art in a wide range of NLP tasks and have also been applied to many real-world products. Understanding the reliability and certainty of transformer model predictions is crucial for building trustable machine…

Computation and Language · Computer Science 2021-12-28 Jiahuan Pei , Cheng Wang , György Szarvas

In this paper, we establish a comprehensive characterization of the generalized Lipschitz classes through the study of the rate of convergence of a family of semi-discrete sampling operators, of Durrmeyer type, in $L^p$-setting. To achieve…

Functional Analysis · Mathematics 2025-11-14 Danilo Costarelli , Michele Piconi , Gianluca Vinti

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such…

Machine Learning · Computer Science 2026-02-02 Shyam Venkatasubramanian , Sean Moushegian , Michael Lin , Mir Park , Ankit Singhal , Connor Lee

The signal differentiation problem involves the development of algorithms that allow to recover a signal's derivatives from noisy measurements. This paper develops a first-order differentiator with the following combination of properties:…

Systems and Control · Electrical Eng. & Systems 2025-04-01 Rodrigo Aldana-Lopez , Richard Seeber , Hernan Haimovich , David Gomez-Gutierrez

Using lattice approximations of Euclidean space, we develop a way to approximate stable processes that are represented by stochastic integrals over Euclidean space. Via a stable version of the Lindeberg-Feller Theorem we show that the…

Probability · Mathematics 2013-02-19 Clément Dombry , Paul Jung

Recently, there has been remarkable progress in reinforcement learning (RL) with general function approximation. However, all these works only provide regret or sample complexity guarantees. It is still an open question if one can achieve…

Machine Learning · Computer Science 2023-05-16 Yue Wu , Jiafan He , Quanquan Gu

We investigate the statistical and computational limits of prompt tuning for transformer-based foundation models. Our key contributions are prompt tuning on \emph{single-head} transformers with only a \emph{single} self-attention layer: (i)…

Machine Learning · Computer Science 2025-06-09 Jerry Yao-Chieh Hu , Wei-Po Wang , Ammar Gilani , Chenyang Li , Zhao Song , Han Liu

The {\L}ojasiewicz inequality characterizes objective-value convergence along gradient flows and, in special cases, yields exponential decay of the cost. However, such results do not directly give rates of convergence in the state. In this…

Optimization and Control · Mathematics 2026-03-30 Andreas Oliveira , Arthur C. B. de Oliveira , Mario Sznaier , Eduardo Sontag

This paper proposes a tractable family of remainder-form mixed-monotone decomposition functions that are useful for over-approximating the image set of nonlinear mappings in reachability and estimation problems. Our approach applies to a…

Optimization and Control · Mathematics 2024-06-25 Mohammad Khajenejad , Sze Zheng Yong

Flow-based methods for sampling and generative modeling use continuous-time dynamical systems to represent a {transport map} that pushes forward a source measure to a target measure. The introduction of a time axis provides considerable…

Machine Learning · Statistics 2025-06-19 Panos Tsimpos , Zhi Ren , Jakob Zech , Youssef Marzouk