English
Related papers

Related papers: Mitigating Transformer Overconfidence via Lipschit…

200 papers

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

Transformer-based models have made remarkable progress in image restoration (IR) tasks. However, the quadratic complexity of self-attention in Transformer hinders its applicability to high-resolution images. Existing methods mitigate this…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Yuang Ai , Huaibo Huang , Tao Wu , Qihang Fan , Ran He

Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the $l_{2}$ norm is useful for adversarial robustness, interpretable gradients and stable training. 1-Lipschitz CNNs are usually designed by enforcing…

Machine Learning · Computer Science 2022-11-17 Sahil Singla , Soheil Feizi

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this…

Machine Learning · Computer Science 2024-06-04 Romain Ilbert , Ambroise Odonnat , Vasilii Feofanov , Aladin Virmaux , Giuseppe Paolo , Themis Palpanas , Ievgen Redko

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Machine Learning · Computer Science 2024-05-07 Yuzhen Mao , Martin Ester , Ke Li

Transformer-based models have recently become wildly successful across a diverse set of domains. At the same time, recent work has shown empirically and theoretically that Transformers are inherently limited. Specifically, they argue that…

Machine Learning · Computer Science 2024-07-30 Gbètondji J-S Dovonon , Michael M. Bronstein , Matt J. Kusner

We introduce a first order Total Variation type regulariser that decomposes a function into a part with a given Lipschitz constant (which is also allowed to vary spatially) and a jump part. The kernel of this regulariser contains all…

Numerical Analysis · Mathematics 2019-12-06 Martin Burger , Yury Korolev , Simone Parisotto , Carola-Bibiane Schönlieb

We consider abstract inverse problems between infinite-dimensional Banach spaces. These inverse problems are typically nonlinear and ill-posed, making the inversion with limited and noisy measurements a delicate process. In this work, we…

Functional Analysis · Mathematics 2022-12-20 Giovanni S. Alberti , Ángel Arroyo , Matteo Santacesaria

We study a sequential binary prediction setting where the forecaster is evaluated in terms of the calibration distance, which is defined as the $L_1$ distance between the predicted values and the set of predictions that are perfectly…

Machine Learning · Computer Science 2024-05-28 Mingda Qiao , Letian Zheng

Behavioral systems define discrete-time LTI systems in terms of a set of trajectories, which forms a linear subspace. This subspace underlies the subspace predictor used in data-driven prediction and control. In practice, such subspaces are…

Optimization and Control · Mathematics 2026-05-26 Dian Jin , Jeremy Coulson

Semantic segmentation tasks naturally require high-resolution information for pixel-wise segmentation and global context information for class prediction. While existing vision transformers demonstrate promising performance, they often…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Yu-Huan Wu , Shi-Chen Zhang , Yun Liu , Le Zhang , Xin Zhan , Daquan Zhou , Jiashi Feng , Ming-Ming Cheng , Liangli Zhen

The quadratic computational cost of the self-attention mechanism is a primary challenge in scaling Transformer models. While attention sparsity is widely studied as a technique to improve computational efficiency, it is almost universally…

Computation and Language · Computer Science 2025-08-11 Sagar Gandhi , Vishal Gandhi

This manuscript bridges nonparametric smoothness-based and shape-restricted estimation, which may appear as two disjoint paradigms in the field. The proposed approach is motivated by a conceptually simple observation: every Lipschitz…

Methodology · Statistics 2026-05-22 Kenta Takatsu , Tianyu Zhang , Arun Kumar Kuchibhotla

The adoption of vision neural networks in regulated industries requires formal robustness guarantees, especially in safety-critical domains such as healthcare, autonomous vehicles, and aerospace. However, current approaches are confined to…

Computer Vision and Pattern Recognition · Computer Science 2026-05-25 Jean-Guillaume Durand , Panagiotis Kouvaros , Maxime Gariel , Alessio Lomuscio

Neural implicit surfaces are a promising tool for geometry processing that represent a solid object as the zero level set of a neural network. Usually trained to approximate a signed distance function of the considered object, these methods…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Guillaume Coiffier , Louis Bethune

In this work, we propose a framework to learn feedback control policies with guarantees on closed-loop generalization and adversarial robustness. These policies are learned directly from expert demonstrations, contained in a dataset of…

Machine Learning · Computer Science 2022-11-03 Abed AlRahman Al Makdah , Vishaal Krishnan , Fabio Pasqualetti

Regularization methods, specifically those which directly alter weights like $L_1$ and $L_2$, are an integral part of many learning algorithms. Both the regularizers mentioned above are formulated by assuming certain priors in the parameter…

Computer Vision and Pattern Recognition · Computer Science 2019-11-01 Avinash Kori , Manik Sharma

Transformers struggle with length generalisation, displaying poor performance even on basic tasks. We test whether these limitations can be explained through two key failures of the self-attention mechanism. The first is the inability to…

Machine Learning · Computer Science 2025-10-07 Mattia Opper , Roland Fernandez , Paul Smolensky , Jianfeng Gao

We study adaptive data-dependent dimensionality reduction in the context of supervised learning in general metric spaces. Our main statistical contribution is a generalization bound for Lipschitz functions in metric spaces that are…

Machine Learning · Computer Science 2015-03-26 Lee-Ad Gottlieb , Aryeh Kontorovich , Robert Krauthgamer

Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-27 Qing Wang , Jiaming Zhang , Kailun Yang , Kunyu Peng , Rainer Stiefelhagen
‹ Prev 1 3 4 5 6 7 10 Next ›